VinThesisTitle.html
updated May 23, 2023
Dssertations/theses with my name in title
256 dissertations
with Wasserstein or Vaserstein in title
Author:Matthias Gelbrich
Thesis, Dissertation, 1987
German
Publisher:1987
1989
[CITATION] (1989). LP-Wasserstein-Metriken und Approximation stochastischer Differentialgleichungen. Ph. D. thesis, Dissert. A, Humboldt-Universitat Berlin.
M Gelbrich - 1989
Lp- Wasserstein metric between measures on Euclidean and Hilbert spaces. (English) Zbl 0711.60003
Math. Nachr. 147, 185-203 (1990).
Reviewer: L.Rüschendorf
1989 thesis
Lp-Wasserstein-Metriken [Lp-Wasserstein-Metriken] und Approximationen stochastischer Differentialgleichungen
Author:Matthias Gelbrich
Thesis, Dissertation, 1989
German
Publisher:1989
View AllFormats & Editions
Author:Matthias Gelbrich (
Author)
Thesis, Dissertation, 1989
German
Publisher:1989
1990 thesis
Lp-Wasserstein-Metriken und Approximationen stochastischer Differentialgleichungen
Author:Matthias Gelbrich
Thesis, Dissertation, 1990
German
Publisher:1990
View AllFormats & Editions
1991
Ph.D. Universidad de Cantabria 1991
Dissertation: Aplicaciones Crecientes. Relaciones con la Métrica de Wasserstein.
Advisor: Juan Antonio Cuesta Albertos
1997
Ph.D. Universidad de Valladolid 1997
Dissertation: Aplicaciones de las Métricas de Wasserstein al Análisis de Datos
Mathematics Subject Classification: 62—Statistics
Advisor 1: Carlos Matran Bea
2006
Hélène Boistard
De Institut de Mathématiques de Toulouse 2006
Dissertation: Asymptotic efficiency of Wasserstein statistics
Mathematics Subject Classification: 62—Statistics
Advisor 1: Eustasio del Barrio
Advisor 2: Fabrice Gamboa
2006 PDF Tartu
Using Gromov-Wasserstein distance to explore sets of networks
pdfs.semanticscholar.org › ...
pdfs.semanticscholar.org › ...
this Master thesis is to study, implement, and apply one Gromov-Wasser- stein type of ... metric measure spaces and compare them on basis of Gromov- Wasserstein distance. ... Nature Reviews Neuroscience, 7(4):318–324, 2006. [2] M.-M.
Reigo HendriksonPublished
2007
PhD Thesis: asymptotic efficiency of tests related with the ...
PhD Thesis with advisors Eustasio del Barrio and Fabrice Gamboa, defended on the 16th of July, 2007, before the tribunal composed by Profesors Jean-Marc Azaïs, Bernard Bercu, Eustasio del Barrio, Fabrice Gamboa and Carlos Matrán.
This thesis is composed of three main parts. In the first part, we study some asymptotic properties of multiple integrals with respect to the empirical process. The second part is devoted to the study of the asymptotic efficiency of the Wasserstein test. The equivalence of the Wasserstein statistic with a double integral with respect to the empirical process allows us to apply the results of the first part. A simulation study is added to the study of the asymptotic power. The third part deals with large deviations for L-statistics. A large deviations principle is obtained using the topology of the Wasserstein distance on the space of measures, under conditions on the extremes.
2008
onstruction of the parallel transport in the Wasserstein ... - cvgmt
cvgmt.sns.it › paper
Construction of the parallel transport in the Wasserstein space. created by ambrosio on 15 Apr 2008. [BibTeX] ... PhD thesis of the second author. Keywords : ...
Author:Matthias Erbar
Thesis, Dissertation, 2008
German
Publisher:2008
<—10 theses till 2008
2009 1
Large deviation principle for empirical measures under wasserstein distance
by Wang, Ran
Translation from original language as provided by authorLet (Xn)n¸1 be a sequence of i.i.d.r.v.'s defined on a probability space with values in a Polish space....
Dissertation/Thesis: Citation Online
2009 2
Hamiltonian systems and the calculus of differential forms on the Wasserstein space
by Kim, Hwa Kil 2009 - Cited by 6
This thesis consists of two parts. In the first part, we study stability properties of Hamiltonian systems on the Wasserstein space. Let H be a Hamiltonian...
Dissertation/Thesis: Citation Online
Kim, Hwa Kil. Hamiltonian systems and the calculus of differential forms on the Wasserstein space.
Degree: PhD, Mathematics, 2009, Georgia Tech
URL: http://hdl.handle.net/1853/29720
► This thesis consists of two parts. In the first part, we study stability properties of Hamiltonian systems on the Wasserstein space. Let H be a… (more)
Subjects/Keywords: Hamiltonian systems; Differential forms; Wasserstein space; Hamiltonian systems; Differential forms
…1.2 Wasserstein space . . . . . . . . . . . . . . . . . . . . . . . . . . . . II… …WASSERSTEIN SPACE 41 3.1 Tangent and Cotangent bundles . . . . . . . . . . . . . . . . . . . . 41… …properties of Hamiltonian systems on the Wasserstein space. Let H be a Hamiltonian satisfying… …forms on the Wasserstein space. Our main result is to prove an analogue of Green’s theorem for… …1-forms and show that every closed 1-form on the Wasserstein space is exact. If the…
Record Details Similar Records Cite Share »
MR2713745 Kim, Hwa Kil; Hamiltonian systems and the calculus of differential forms on the Wasserstein space. Thesis (Ph.D.)–Georgia Institute of Technology. 2009. 87 pp. ISBN: 978-1109-37242-7, ProQuest LLC, Thesis
book 2011 above
Hwa Kil Kim
Ph.D. Geor\gia Institute of Technology 2009
Dissertation: Hamiltonian systems and the calculus of differential forms on the Wasserstein space
Advisor 1: Wilfrid Gangbo
2009 3
高津, 飛鳥. On Wasserstein geometry of the space of Gaussian measures
Degree: 理学, 2009, Tohoku University / 東北大学
URL: http://hdl.handle.net/10097/40123
書誌のみ Advisors/Committee Members: 山田澄生.
Record Details Similar Records Cite Share »
2009 4 modified Georga Tech
Hamiltonian systems and the calculus of differential forms on the Wasserstein space
by Kim, Hwa Kil
This thesis consists of two parts. In the first part, we study stability properties of Hamiltonian systems on the Wasserstein space. Let H be a Hamiltonian...
Dissertation/ThesisCitation Online
2009 5
Hamiltonian systems and the calculus of differential forms on the Wasserstein space
Kim, Hwa Kil. Georgia Institute of Technology. ProQuest Dissertations Publishing, 2009. 3376305.
Abstract/DetailsPreview - PDF (204 KB)Full text - PDF (962 KB)
Order a copy
2009 6
Large deviation principle for empirical measures under wasserstein distance
Wang, Ran. Wuhan University (People's Republic of China). ProQuest Dissertations Publishing, 2009. 10409094.
< —15 titles till 2009
+ 6 titles in 2009
= 21 tithes till 2009
end 2009
start 2010
2010
Asuka Takatsu
Ph.D. Tohoku University 2010
Dissertation: On Wasserstein geometry of the space of Gaussian measures.
Mathematics Subject Classification: 53—Differential geometry
Advisor 1: Sumio Yamada
Using Gromov-Wasserstein distance to explore sets of networks
pdfs.semanticscholar.org › ...
PDF 2010 ? -> 2016? see 2015
Reigo Hendrikson Published 2016 Mathematics
this Master thesis is to study, implement, and apply one Gromov-Wasser- stein type of distance ... metric measure spaces and compare them on basis of Gromov -Wasserstein distance. Keywords: ... 1):D463–D467, 2010. [5] A. Madan, M
2010
Geometry and Stochastic Calculus on Wasserstein spaces
C Selinger - 2010 - orbilu.uni.lu
PhD Thesis under the supervision of Prof. Anton Thalmaier at Université du Luxembourg, September
2010 … 1.1 Weak topology and optimal transport distance . . . . . . . . . . 12 1.2 Topology of smooth
curves . . . . . . . . . . . . . . . . . . . . . 19 … 2.1 Wasserstein geodesics . . . . . . . . . . . . . . . . . . . . . . . . 25 …
Related articles All 3 versions
< —24 till 2010
2012
by Lopes, Luciene Pinheiro
Tese (doutorado)—Universidade de Brasília, Instituto de Ciências Exatas, Departamento de Matemática, 2012. Neste trabalho propomos testes não-paramétricos para...
Dissertation/ThesisCitation Online
<-25 theses till 2012
end 2012
start 2913
2013 1 Technische Universiteit Eindhoven
Open Access
bynRenger, D.R.M
The discovery of Wasserstein gradient flows provided a mathematically precise formulation for the way in which thermodynamic systems are driven by entropy....
Dissertation/ThesisCitation Online
2013 2
[Chinese Quantile regression based on ℓ1-regularization and Bernstein approximation of distribution under Wasserstein distance by Tian Wei ]
复旦大学, 2013
硕士: 应用数学; O241.5;O212.1;...
Dissertation/ThesisCitation Online
2013 3
[Chinese Design and Implementation of Color Transfer Algorithm Based on Wasserstein Distance by Feng Wenya ]
by 冯文雅
颜色迁移(Color...
Dissertation/ThesisCitation Online
2013 4
Thibaut Le Gouic
Ph.D. Université Paul Sabatier - Toulouse III 2013
Dissertation: Localisation de masse et espaces de Wasserstein
Mathematics Subject Classification: 60—Probability theory and stochastic processes
Advisor 1: Philippe Berthet
2013 5
Microscopic interpretation of Wasserstein gradient flows
PDF Eindhoven U of Technology
Jan 1, 2013 - out this thesis. Let me mention here that convergence of measures in the Wasserstein metric coincides with narrow convergence (defined in ...
15. Renger, D.R.M. Microscopic interpretation of Wasserstein gradient flows.
Degree: 2013, Technische Universiteit Eindhoven
URL: https://research.tue.nl/nl/publications/microscopic-interpretation-of-wasserstein-gradient-flows(4a579041-a911-4cee-9c77-3bc7924caff2).html ; urn:nbn:nl:ui:25-4a579041-a911-4cee-9c77-3bc7924caff2 ; 4a579041-a911-4cee-9c77-3bc7924caff2 ; 10.6100/ir749143 ; urn:isbn:978-90-386-3329-9 ; urn:nbn:nl:ui:25-4a579041-a911-4cee-9c77-3bc7924caff2 ; https://research.tue.nl/nl/publications/microscopic-interpretation-of-wasserstein-gradient-flows(4a579041-a911-4cee-9c77-3bc7924caff2).html
► The discovery of Wasserstein gradient flows provided a mathematically precise formulation for the way in which thermodynamic systems are driven by entropy. Since the entropy… (more)
2013 6
Entropic Gradient Flows on the Wasserstein Space via Large Deviations fromThermodynamic Limit
PDF U of Bath 2013 Ph.D.
by V Laschos - 2013 - Related articles
Feb 7, 2014 - This copy of the thesis has been supplied on the condition that ... the Wasserstein space, bringing this way the statistical mechanics point of ...
2013 7
Geometry and Stochastic Calculus on Wasserstein spaces
PDF U du Luxembourg 2010 Ph.D.
by Christian Selinger - 2010 — Université du Luxembourg— Related articles
The main object of interest in the present thesis is P(M) – the space of proba- bility measures on a Riemannian manifold (M,g) endowed with the Wasserstein.
Record Details Similar Records Cite Share »
Georg-August-Universität Göttingen
Selinger
2013 8 U of Bath
Entropic gradient flows on the wasserstein space via large deviations from thermodynamic limits
by Laschos, Vaios
In a seminal work, Jordan, Kinderlehrer and Otto proved that the Fokker-Planck equation can be described as a gradient flow of the free energy functional in...
Dissertation/Thesis: Citation Online
Laschos, Vaios. Entropic gradient flows on the Wasserstein space via large deviations from thermodynamic limits.
Degree: PhD, 2013, University of Bath
URL: https://researchportal.bath.ac.uk/en/studentthesis/entropic-gradient-flows-on-the-wasserstein-space-via-large-deviations-from-thermodynamic-limits(95755edc-f761-4eb1-a39b-3b2044610ad7).html ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.589659
► In a seminal work, Jordan, Kinderlehrer and Otto proved that the Fokker-Planck equation can be described as a gradient flow of the free energy functional… (more)
Subjects/Keywords: 519
Record Details Similar Records Cite Share »
Tohoku University / 東北大学
Laschos, Vaios. Entropic Gradient Flows on the Wasserstein Space via Large Deviations from Thermodynamic Limits.
Degree: phd, 2013, University of Bath
URL: http://opus.bath.ac.uk/38516/
► In a seminal work, Jordan, Kinderlehrer and Otto proved that the Fokker- Planck equation can be described as a gradient flow of the free energy… (more)
…x5D;, the authors show that this holds for the Wasserstein space (P2 (Rd )… …structure (see chapter 5) in Wasserstein space is the Laplacian. This gives rise to… …20] the author proves that τ Jτ (·|µ0 ) Gamma-converges to the Wasserstein… …metric W2 (·, µ0 ) as τ goes to 0, recovering this way the Wasserstein distance from… …gradient flow of the free energy on the Wasserstein space, by studying the large deviations of…
Record Details Similar Records Cite Share »
2013 9
Microscopic interpretation of Wasserstein gradient flows
DRM Renger - 2013 - oatd.org
Open Access Theses and Dissertations … be related to the large deviations of stochastic particle
systems, the question arises whether a similar relation exists between Wasserstein gradient flows …
In the work presented in this thesis, such relation is studied for a number of systems …
Cited by 9 Related articles All 4 versions
2013 10 Berlin
Entropic gradient flows on the Wasserstein space via large deviations from thermodynamic limits
by Laschos, Vaios
In a seminal work, Jordan, Kinderlehrer and Otto proved that the Fokker-Planck equation can be described as a gradient flow of the free energy functional in...
Dissertation/ThesisCitation Online
2013 11
Entropic gradient flows on the wasserstein space via large deviations from thermodynamic limits
Laschos, Vaios. University of Bath (United Kingdom). ProQuest Dissertations Publishing, 2013. U637267.
2013 12 thesis
Microscopic interpretation of Wasserstein gradient flows
Authors:D.R.M. Renger, Renger, D.R.M. (Creator)
Summary:The discovery of Wasserstein gradient flows provided a mathematically precise formulation for the way in which thermodynamic systems are driven by entropy. Since the entropy of a system in equilibrium can be related to the large deviations of stochastic particle systems, the question arises whether a similar relation exists between Wasserstein gradient flows and stochastic particle systems. In the work presented in this thesis, such relation is studied for a number of systems. As explained in the introduction chapter, central to this research is the study of two types of large deviations for stochastic particle systems. The first type is related to the probability of the empirical measure of the particle system, after a fixed time step, conditioned on the initial empirical measure. The large-deviation rate provides a variational formulation of the transition between two macroscopic measures, in fixed time. This formulation can then be related to a discrete-time formulation of a gradient flow, known as minimising movement. To this aim, a specific small-time development of the rate is used, based on the concept of Mosco- or Gamma-convergence. The other type of large deviations concerns the probability of the trajectory of the empirical measure in a time interval. For these large deviations, the rate provides a variational formulation for the trajectory of macroscopic measures. For some systems, this rate can be related to a continuous-time formulation of gradient flows, known as an entropy-dissipation inequality. Chapter 2 serves as background, where a number of results from particle system theory and large deviations are proven in a general setting. In particular, the generator of the empirical measure is calculated, the many-particle limit of the empirical measure is proven, and the discrete-time large deviation principle is proven. In Chapter 3, the discrete-time large-deviation rate is studied for a system of independent Brownian particles in a force field, whichShow more
Thesis, Dissertation, 2013
English
Publisher:Technische Universiteit Eindhoven, 2013
<—27 theses before 2913
+ 12 titles in 2013
= 37 tutles till 2013
end 2013
start 2014
2014 1
The exponential formula for the Wasserstein metric
by Craig, Katy
Many evolutionary partial differential equations may be rewritten as the gradient flow of an energy functional, a perspective which provides useful estimates...
Dissertation/Thesis: Citation Online
Craig, Katy, 1985-. The exponential formula for the Wasserstein metric.
Degree: Mathematics, 2014, Rutgers University
URL: https://rucore.libraries.rutgers.edu/rutgers-lib/44068/
Subjects/Keywords: Differential equations; Partial – Numerical solutions
Record Details Similar Records Cite Share »
University of Bath
also a book ?MR3295393 Thesis Craig, Katy The exponential formula for the Wasserstein metric. Thesis (Ph.D.)–Rutgers The State University of New Jersey - New Brunswick. 2014. 80 pp. ISBN: 978-1321-29355-5, ProQuest LLC
2014 2
Optimal Transport and the Wasserstein Metric
PDF Rio de Janero
byPaulo Najberg Orenstein - 2014 - Related articles
Jan 23, 2014 - Optimal Transport and the Wasserstein Metric. Dissertaç˜ao de Mestrado. Thesis presented to the Postgraduate Program in Applied Math-.
2014 3
The Exponential Formula for the Wasserstein ... - UCSB Math
PDF Rutgers
by K Craig - 2014 - Cited by 9 - Related articles
Apr 6, 2014 - In this thesis, we consider gradient flow in the Wasserstein metric, a metric on the space of probability measures that shares many properties ...
The Exponential Formula for the Wasserstein ... - UCSB Math
Apr 6, 2014 — A dissertation submitted to Rutgers, The State University of New Jersey, in partial ... In this thesis, we consider gradient flow in the Wasserstein metric, a metric on the space of ... for Nonlinear Analysis, June 7-12, 2010. Lecture ...
by K Craig · 2014 · Cited by 11 · Related articles
2014 4
Kell, Martin. On curvature conditions using Wasserstein spaces.
Degree: PhD, Mathematik und Informatik, 2014, Universität Leipzig
URL: http://nbn-resolving.de/urn:nbn:de:bsz:15-qucosa-149614
► This thesis is twofold. In the first part, a proof of the interpolation inequality along geodesics in p-Wasserstein spaces is given and a new curvature… (more)
Record Details Similar Records Cite Share »
University of Waterloo
2014 5 master thesis
[PDF] Phase retrieval on the quadratic Wasserstein space
A Tsipenyuk - www-m7.ma.tum.de
X-ray crystallography is the main tool for the structural analysis of molecules today. One of its main subtasks is the phase retrieval problem. In this thesis, the phase retrieval problem is discussed in the context of the optimal transport. Phase retrieval is formulated as an energy …
Related articles All 2 versions
2014 6
by Bowles, Malcolm
In this thesis, we study a linear fractional Fokker-Planck equation that models non-local (`fractional') diffusion in the presence of a potential field. The...
Dissertation/ThesisCheck Library
Weak Solutions to a Fractional Fokker-Planck Equation via Splitting and Wasserstein Gradient Flow
2014 7
Phase retrieval on the quadratic Wasserstein space
https://www-m7.ma.tum.de › pub › mathe_thesis
https://www-m7.ma.tum.de › pub › mathe_thesis
PDFby A Tsipenyuk — I assure the single handed composition of this master's thesis only supported by declared resources. ... 2Optimal transport and quadratic Wasserstein space.
2014 8 Technische Universit¨at München master thesis
[PDF] Phase retrieval on the quadratic Wasserstein space
A Tsipenyuk - www-m7.ma.tum.de
X-ray crystallography is the main tool for the structural analysis of molecules today. One of its main subtasks is the phase retrieval problem. In this thesis, the phase retrieval problem is discussed in the context of the optimal transport. Phase retrieval is formulated as an energy …
Related articles All 2 versions
2014 9
The exponential formula for the Wasserstein metric
Craig, Katy. Rutgers The State University of New Jersey - New Brunswick. ProQuest Dissertations Publishing, 2014. 3642504.
Abstract/DetailsPreview - PDF (415 KB)Full text - PDF (1 MB)
<—39 titles before 2014
+ 9 titles in 2014
= 46 titles till 2014
end 2014
start 2015
2015
PDF Reigo Hendrikson
Published 2016 Mathematics Tartu Ph.D.
this Master thesis is to study, implement, and apply one Gromov-Wasser- stein type of distance ... metric measure spaces and compare them on basis of Gromov-Wasserstein distance. Keywords: ... all x, y ∈ X, it holds: 1 November 5th, 2015. 7 ...
2015
Gram-Schmidt-Vaserstein generators for odd sized elementary groups
Chattopadhyay, Pratyusha; Rao, Ravi A. arXiv.org; Ithaca, Nov 27, 2015.
<—47 titles before 2015
+ 2 titles in 2015
= 49 titles till 2015
end 2015 2 theses
start 2016
2016 1
Systèmes de particules en interaction, approche par flot de gradient dans l'espace de Wasserstein
by Laborde, Maxime
Depuis l’article fondateur de Jordan, Kinderlehrer et Otto en 1998, il est bien connu qu’une large classe d’équations paraboliques peuvent être vues comme des...
Dissertation/Thesis: book ok
Publication Statement: [S.l.] : University Paris Sciences et Lettres, 2016.
Full Text Online
Laborde, Maxime. Systèmes de particules en interaction, approche par flot de gradient dans l'espace de Wasserstein : Interacting particles systems, Wasserstein gradient flow approach.
Degree: Docteur es, Sciences, 2016, Paris Sciences et Lettres
URL: http://www.theses.fr/2016PSLED014
Depuis l’article fondateur de Jordan, Kinderlehrer et Otto en 1998, il est bien connu qu’une large classe d’équations paraboliques peuvent être vues comme des flots… (more)
Subjects/Keywords: Distance de Wasserstein; Flots de gradient; Schéma JKO; Splitting; Dérive non locale; Diffusions non linéaires; Diffusions croisées; Systèmes de réaction-Diffusion; Équations d'Hele-Shaw; Transport optimal; Transport multi-Marges; Formule de Benamou-Brenier; Lagrangien augmenté; Mouvement de foules; Espèces en interaction; Wasserstein distance; Gradient flows; JKO scheme; Splitting; Nonlocal drift; Nonlinear diffusions; Cross-Diffusion; Reaction-Diffusion systems; Hele-Shaw equation; Optimal transport; Multi-Marginal transport; Benamou-Brenier formula; Augmented lagrangian; Crowd motions; Interacting species; 519.2
Record Details Similar Records Cite Share »
University of Victoria
ystèmes de particules en interaction, approche par flot de gradient dans l'espace de Wasserstein
2016 2
Using Gromov-Wasserstein distance to explore sets of networks
PDF University of Tartu 2016
by R Hendrikson - Cited by 4 - Related articles
this Master thesis is to study, implement, and apply one Gromov-Wasser- ... metric measure spaces and compare them on basis of Gromov-Wasserstein distance ...
2016 3
Numerical Schemes for Calculating the Discrete Wasserstein Distance
PDF Bonn 2016
by B Cabrera - 2016 - Related articles
Feb 26, 2016 - The problem we are focusing on in this thesis is the Wasserstein distance on discrete (finite) sets. We will see later that the original Wasserstein ...
2016 4
Using Gromov-Wasserstein distance to explore sets of networks
... thesis is to study, implement, and apply one Gromov-Wasserstein type of distance introduced by F.Memoli (2011) in his paper "Gromov-Wasserstein Distances .. 2016
2016 5
Using Gromov-Wasserstein distance to explore sets of networks
R Hendrikson - 2016 - web-proxy.io
… The aim of this Master thesis is to study, implement, and apply one Gromov-Wasser- stein type
of distance introduced by F.Mémoli (2011) in his paper ”Gro- mov–Wasserstein Distances and
the Metric Approach to Object Matching” to study sets of complex networks …
2016 6
Interacting particles systems, Wasserstein gradient flow approach
by Laborde, MaximEcole doctorale SDOSE (Paris), 2016
Since 1998 and the seminal work of Jordan, Kinderlehrer and Otto, it is well known that a large class of parabolic equations can be seen as gradient flows in...
Dissertation/ThesisCitation Online
2016 7 master Hong Kong
Existence of Solutions to Wasserstein Gradient Flows and Their Long Time Asymptotic Behaviors
Ng, Wing Kit. Thesis M.Phil. Chinese University of Hong Kong 2016. Includes bibliographical references (leaves ). Abstracts also in Chinese. Title from PDF...
Dissertation/ThesisCitation Online
2016 8 master
[PDF] Using Gromov-Wasserstein distance to explore sets of networks
R Hendrikson - University of Tartu, Master Thesis, 2016 - core.ac.uk
In many fields such as social sciences or biology, relations between data or variables are
presented as networks. To compare these networks, a meaningful notion of distance
between networks is highly desired.
The aim of this Master thesis is to study, implement, and …
2016 9
Baricentros en el espacio de Wasserstein: aplicación a modelos estadísticos de deformación
Authors:Gordaliza Pastor, Paula (Contributor), Barrio Tellado, Eustasio del (Creator), Universidad de Valladolid Facultad de Ciencias (Creator)
Summary:En el análisis de la homogeneidad de una colección de distribuciones y de relaciones estructurales entre las observaciones, son muy útiles los baricentros y la variación en distancia de Wasserstein. Estudiamos la estimación de los cuantiles del proceso empírico de la variación de Wasserstein mediante un procedimiento bootstrap. Después, usamos los resultados obtenidos para hacer inferencia estadística bajo un modelo de deformación paramétrico. En particular, calculamos el valor de la variación y de los parámetros óptimos cuando las observaciones satisfacen un modelo de localización y escala. Enunciamos un teorema central del límite para la variación de Wasserstein, útil para construir un test basado en dicho estadístico, que comprueba la homogeneidad de distribuciones. Finalmente, presentamos resultados de simulaciones llevadas a cabo, en diferentes escenarios, para verificar la bondad del testShow more
Thesis, Dissertation, 2016
Spanish
Publisher:2016
<—49 before 2016
+ 9 titles in 2016
= 58 dissertations till 2016
end 2016
start 2017
2017 1
Malte Laurens Kampschulte
Dr. rer. nat. Rheinisch-Westfälische Technische Hochschule Aachen 2017
Dissertation: Gradient flows and a generalized Wasserstein distance in the space of Cartesian currents
Mathematics Subject Classification: 49—Calculus of variations and optimal control
Advisor 1: Christof Melcher
Gradient flows and a generalized Wasserstein distance in the space of Cartesian currents
2017 2
Wasserstein Generative Adversarial Network
Wenbo Gong
Department of Engineering University of Cambridge
Aug 2017 Master
2017 3
Walsh, Joseph Donald. The boundary method and general auction for optimal mass transportation and Wasserstein distance computation.
Degree: PhD, Mathematics, 2017, Georgia Tech
URL: http://hdl.handle.net/1853/58701
► Numerical optimal transport is an important area of research, but most problems are too large and complex for easy computation. Because continuous transport problems are… (more)
Subjects/Keywords: Optimal transportation; Auction methods; Numerical analysis; Optimization; Algorithm design; Monge; Kantorovich; Wasserstein
…Computing the Wasserstein distance over boxes xr . . . . . . . . . 148 5.4.4 Reconstructing the… …Accuracy of the Wasserstein distance . . . . . . . . . . . . . . . . 157 5.5.4 Reconstruction… …5.3 Wasserstein approximation and error values for the NWSE problem . . . . 159 5.4… …Wasserstein approximation and error values for the 4 × 4 problem . . . . . 160 5.5 Wasserstein… …problem . . . . . . . . . . . . . . . . . . . 161 5.7 Wasserstein distance approximation with…
Record Details Similar Records Cite Share »
2017 4
Gradient flows and a generalized Wasserstein distance in the ...
www.math1.rwth-aachen.de › rwzh › file › lidx
flows and a generalized Wasserstein distance in the space of Cartesian currents. Aachen (2017, 2018) [Dissertation / PhD Thesis]. Page(s): 1 ...
Gradient flows and a generalized Wasserstein distance in the ...
www.math1.rwth-aachen.de › rwzh › file › lidx
Gradient flows and a generalized Wasserstein distance in the space of Cartesian currents. Aachen (2017, 2018) [Dissertation / PhD Thesis]. Page(s): 1 ...
2017 5
[Chinese 3D graphics matching method based on Gromov-Wasserstein distance by Jiao Yanyan]
by 焦艳艳 K MYUNGHEE CHO
大连理工大学, 2017
硕士: 计算数学; TP391.41;...
Dissertation/ThesisCitation Online
2017 6
by Lessel, Bernadette Göttingen 1918 defended in June 1918. See video
Advisor 1: Thomas Schick
Dissertation/ThesisCitation Online
2017 7
[French Habilitation to Direct Research: Central limit theorem, inequalities of concentration and principles of large deviations: applications to models resulting from combinatorics and to sensitivity analysis. Minimax bounds and Wasserstein distance in semi-parametric statistics]
T Klein - 2016 - hal.archives-ouvertes.fr
HAL is a multi-disciplinary open access archive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers …
Related articles All 3 versions
2017 t8 hesis
Wasserstein Distance on Finite Spaces: Statistical Inference and Algorithms
Authors:Max Sommerfeld, Axel Munk, Stephan Huckemann
Summary:Wasserstein distances or, more generally, distances that quantify the optimal transport between probability measures on metric spaces have long been established as an important tool in probability theory. More recently, it has found its way into statistical theory, applications and machine learning - not only as a theoretical tool but also as a quantity of interest in its own right. Examples include goodness-of-fit, two-sample and equivalence testing, classification and clustering, exploratory data analysis using Fr ́echet means and geodesics in the Wasserstein metric. This advent of the Wa..Show more
Thesis, Dissertation, 2017
English
Publisher:Niedersächsische Staats- und Universitätsbibliothek Göttingen, Göttingen, 2017
View AllFormats & Editions
2017 9 thesis
Fréchet means in Wasserstein space : theory and algorithms
Authors:Yoav Zemel, Victor M. Panaretos
Summary:Mots-clés de l'auteur: Fréchet mean ; functional data analysis ; geodesic variation ; optimal transportation ; phase variation ; point process ; random measure ; registration ; warping ; Wasserstein distanceShow more
Thesis, Dissertation, 2017
English
Publisher:Ecole Polytechnique Fédérale de Lausanne, Lausanne, 2017
<— 58 before 2017
+ 9 tittles in 2017
= 67 titles till 2017
end 2017
start 2018
2018 1
by Cazelles, Elsa
Cette thèse se concentre sur l'analyse de données présentées sous forme de mesures de probabilité sur R^d. L'objectif est alors de fournir une meilleure...
Dissertation/Thesis:
Full Text Online
Propriétés statistiques du barycentre dans l’espace de Wasserstein
by Cazelles, Elsa
11. Cazelles, Elsa. Statistical properties of barycenters in the Wasserstein space and fast algorithms for optimal transport of measures : Propriétés statistiques du barycentre dans l’espace de Wasserstein.
Degree: Docteur es, Mathématiques appliquées et calcul scientifique, 2018, Bordeaux
URL: http://www.theses.fr/2018BORD0125
Cette thèse se concentre sur l'analyse de données présentées sous forme de mesures de probabilité sur R^d. L'objectif est alors de fournir une meilleure compréhension… (more)
Subjects/Keywords: Espace de Wasserstein; Barycentre; Acp; Transport optimal régularisé; Test d'hypothèse; Analyse statistique; Wasserstein space; Barycenter; Pca; Regularized optimal transport; Hypothesis testing; Statistical analysis
Record Details Similar Records Cite Share »
2018 2
Sn vaserstein's power operation on elementary orbitshape Space in Terms of Wasserstein Geometry and Application to Quantum Physics
Bernadette Lessel -Universität Göttingen 2018
This thesis offers a mathematical framework to treat quantum dynamics without reference to a background structure, but rather by means of the change of the shape of the state. For this, Wasserstein geometry is used. The so called Shape space, then, is defined as the quotient space of a Wasserstein space modulo the action of the
Lessel, Bernadette. Shape space in terms of Wasserstein geometry and application to quantum physics.
Degree: PhD, Mathematik und Informatik, 2018, Georg-August-Universität Göttingen
URL: http://hdl.handle.net/11858/00-1735-0000-002E-E512-4
► This thesis offers a mathematical framework to treat quantum dynamics without reference to a background structure, but rather by means of the change of the… (more)
Record Details Similar Records Cite Share »
Lessel
2018 3
Applications of Wasserstein Distance in Distributionally Robust Optimization
by Wang, Ye
Recent research on formulating and solving distributionally robust optimization problems has seen many different approaches for describing one’s ambiguity set,...
Dissertation/Thesis: Citation Online
Applications of Wasserstein distance in distributionally robust optimization
University of Southern California Dissertations and Theses (16) arrow ... In this dissertation, we use Wasserstein distance to characterize the ambiguity set of .
Wang,
2018 4
A Comparative Assessment of the Impact of Various Norms on Wasserstein Generative Adversarial...
by Ramesh, Chandini
Generative Adversarial Networks (GANs) provide a fascinating new paradigm in machine learning and artificial intelligence, especially in the context of...
Dissertation/Thesis: Citation Online
Ramesh, Chandini. A Comparative Assessment of the Impact of Various Norms on Wasserstein Generative Adversarial Networks.
Degree: MS, Computer Science (GCCIS), 2019, Rochester Institute of Technology
URL: https://scholarworks.rit.edu/theses/9989
Generative Adversarial Networks (GANs) provide a fascinating new paradigm in machine learning and artificial intelligence, especially in the context of unsupervised learning. GANs are… (more)
Subjects/Keywords: Generative adversarial networks; LASSO regression; Norms; Ridge regression; Wasserstein distance; Wasserstein generative adversarial networks
Record Details Similar Records Cite Share »
Technische Universiteit Eindhoven
2018 5
| Wasserstein β-Diversity Metrics over Graphs: Derivation, Efficient Computation and Applications
Oregon State U Ph.D. 2018 by Jason McClelland, advisor Koslicki
In the following we develop metagenomic tools arising from the classic Wasserstein metric as applied to questions regarding the diversity between microbial ...
2018 6
The Entropy-Regularized Wasserstein Distance as a Metric for Machine LearningBased Post-Processing of StructuralMR Images of the Brain
PDF Master of Science Münster
by J Braunsmann - 2018 - Related articles
This thesis treats the Wasserstein distance and its applicability as a metric between magnetic resonance images of the brain, represented as densities on a
2018 7
Data-driven distributionally robust optimization using the ...
by PM Esfahani - 2018 - Cited by 338 - Related articles
Jul 7, 2017 - ... of the PhD thesis [54], which reformulates a distributionally robust two-stage unit commitment problem over a Wasserstein ambiguity set as a ...
2018 8
Nathawut Phandoidaen 2018
Minimax estimation of Wasserstein barycenters
sip.math.uni-heidelberg.de › Masterarbeit-Nathawut-Phandoidaen
Apr 11, 2018 - Thesis: Master in Mathematics; Author: Nathawut Phandoidaen; Title: Minimax estimation of Wasserstein barycenters; Supervisor: Jan ...
2018 9
J Braunsmann - 2018 - uni-muenster.de
This thesis treats the Wasserstein distance and its applicability as a metric between
magnetic resonance images of the brain, represented as densities on a voxel grid. We aim
to use the Wasserstein distance for dimensionality reduction of MR images by using it as a …
Related articles All 2 versions
2018 10
Jason McClelland
Ph.D. Oregon State University 2018
Dissertation: Wasserstein
-Diversity Metrics over Graphs: Derivation, Efficient Computation and Applications
Mathematics Subject Classification: 92—Biology and other natural sciences
Advisor 1: David Koslicki
2018 11
Leuchtenberger, Alina Franziska. The Wasserstein Distance and its Application to Generative Adversarial Networks.
Degree: 2018, University of Vienna
URL: http://othes.univie.ac.at/55841/
In dieser Arbeit geht es um die Wasserstein-Distanz, die die optimalen Transportkosten zwischen zwei Wahrscheinlichkeitsmaßen misst. Diese Distanz ist stetig und eine Konvergenz in der… (more)
Subjects/Keywords: 31.80 Angewandte Mathematik; Neuronale Netzwerke / Distanzen von Wahrscheinlichkeitsverteilungen / Wasserstein Distanz / Generative Adversarial Network / Wasserstein Generative Adversarial Network / Earth-Mover Distanz; neural networks / probability distance / Wasserstein distance / Generative Adversarial Network / Wasserstein Generative Adversarial Network / Earth-Mover distance
URL: http://othes.univie.ac.at/55841/
2018 12
PDF 2018
Graph clustering and the nuclear Wasserstein metric. Thesis by: Daniel de Roux. Advised by: Mauricio Velasco. In Partial Fulfillment of the Requirements.
by D Roux Uribe
2018 13
January 10th, 2018 Thesis Defense Charlie Frogner, Poggio Lab
bcs.mit.edu/.../learning-and-inference-wasserstein-metrics
This thesis develops new approaches for three problems in machine learning, using tools from the study of optimal transport (or Wasserstein) distances between probability distributions. Optimal transport distances capture an intuitive notion of similarity between distributions, by incorporating the underlying geometry of the domain of the ...
2018 14
Learning and inference with Wasserstein metrics / by Charles Frogner.
by Frogner, Charles (Charles Albert)
2018 MIT book
supervised by Tomaso Poggio.
2018 15
Statistical properties of barycenters in the Wasserstein space and fast algorithms for optimal transport of...
by Cazelles, Elsa
2018
Cette thèse se concentre sur l'analyse de données présentées sous forme de mesures de probabilité sur R^d. L'objectif est alors de fournir une meilleure...
Dissertation/ThesisFull Text Online
2018 16
Learning and inference with Wasserstein metrics
Frogner, Charles (Charles Albert) January 2018 (has links)
Thesis: Ph. D., Massachusetts Institute of Technology, Department of Brain and Cognitive Sciences, 2018. / Cataloged from PDF version of thesis. / Includes bibliographical references (pages 131-143). / This thesis develops new approaches for three problems in machine learning, using tools from the study of optimal transport (or Wasserstein) distances between probability distributions. Optimal transport distances capture an intuitive notion of similarity between distributions, by incorporating the underlying geometry of the domain of the distributions. Despite their intuitive appeal, optimal transport distances are often difficult to apply in practice, as computing them requires solving a costly optimization problem. In each setting studied here, we describe a numerical method that overcomes this computational bottleneck and enables scaling to real data. In the first part, we consider the problem of multi-output learning in the presence of a metric on the output domain. We develop a loss function that measures the Wasserstein distance between the prediction and ground truth, and describe an efficient learning algorithm based on entropic regularization of the optimal transport problem. We additionally propose a novel extension of the Wasserstein distance from probability measures to unnormalized measures, which is applicable in settings where the ground truth is not naturally expressed as a probability distribution. We show statistical learning bounds for both the Wasserstein loss and its unnormalized counterpart. The Wasserstein loss can encourage smoothness of the predictions with respect to a chosen metric on the output space. We demonstrate this property on a real-data image tagging problem, outperforming a baseline that doesn't use the metric. In the second part, we consider the probabilistic inference problem for diffusion processes. Such processes model a variety of stochastic phenomena and appear often in continuous-time state space models. Exact inference for diffusion processes is generally intractable. In this work, we describe a novel approximate inference method, which is based on a characterization of the diffusion as following a gradient flow in a space of probability densities endowed with a Wasserstein metric. Existing methods for computing this Wasserstein gradient flow rely on discretizing the underlying domain of the diffusion, prohibiting their application to problems in more than several dimensions. In the current work, we propose a novel algorithm for computing a Wasserstein gradient flow that operates directly in a space of continuous functions, free of any underlying mesh. We apply our approximate gradient flow to the problem of filtering a diffusion, showing superior performance where standard filters struggle. Finally, we study the ecological inference problem, which is that of reasoning from aggregate measurements of a population to inferences about the individual behaviors of its members. This problem arises often when dealing with data from economics and political sciences, such as when attempting to infer the demographic breakdown of votes for each political party, given only the aggregate demographic and vote counts separately. Ecological inference is generally ill-posed, and requires prior information to distinguish a unique solution. We propose a novel, general framework for ecological inference that allows for a variety of priors and enables efficient computation of the most probable solution. Unlike previous methods, which rely on Monte Carlo estimates of the posterior, our inference procedure uses an efficient fixed point iteration that is linearly convergent. Given suitable prior information, our method can achieve more accurate inferences than existing methods. We additionally explore a sampling algorithm for estimating credible regions. / by Charles Frogner. / Ph. D.
2018 17
online
|
Statistical properties of barycenters in the Wasserstein space and fast algorithms for optimal...
by Cazelles, Elsa
Cette thèse se concentre sur l'analyse de données présentées sous forme de mesures de probabilité sur R^d. L'objectif est alors de fournir une meilleure...
Dissertation/ThesisFull Text Online
2018 18
Towards high resolution video generation with progressive growing of sliced Wasserstein GANs
D Acharya, Z Huang, DP Paudel, L Van Gool - arXiv preprint arXiv …, 2018 - arxiv.org
… Page 4. Page 5. Acknowledgements I am highly indebted to Dr. Zhiwu Huang and Dr. Danda
Paudel for their supervision and support during the thesis. Content related to Sliced Wasserstein
Gan in section 5 w
2018 19
[Chinese Research on Image Generation Cyclic Adversarial Network Model and Its Application Based on Wasserstein Distance by Zhang Chunping '
by 张春平
重庆大学, 2018
硕士: 计算机科学与技术; TU9;TP3
Dissertation/ThesisCitation Online
2018 20
by Kang-Chi Ho;
何岡秩
碩士 國立臺灣科技大學 機械工程系 106 We propose the Disentangled Representation Learning on a Wasserstein Generative Adversarial Network with Gradient Penalty, or abbreviated...
Dissertation/ThesisCitation Online
2018 21
Wasserstein Adversarial Domain Adaptation
by 呂昱穎;
Lyu, Yu-Ying
碩士 國立交通大學 電機工程學系 107 Deep learning has achieved a great success in many real-world applications ranging the fields from computer vision to natural language...
Dissertation/ThesisCitation Online
2018 22 PDF
Natural gradient in Wasserstein statistical manifold=1arxiv ...
yifanc96.github.io › slides › Wasserstein_geometry
Jun 4, 2018 — Optimal transport provides the Wasserstein distance among histograms, relying on the structure of sample space (ground cost c). Denote ρ0 ...
Natural gradient in Wasserstein statistical manifold1 undergraduate thesis Yifan Chen Department of Mathematical Sciences Tsinghua University
Learning and Inference with Wasserstein Metrics
Frogner, Charles. Massachusetts Institute of Technology. ProQuest Dissertations Publishing, 2018. 13876650.
A Comparative Assessment of the Impact of Various Norms on Wasserstein Generative Adversarial Networks
Ramesh, Chandini. Rochester Institute of Technology. ProQuest Dissertations Publishing, 2018. 13807809.
Abstract/DetailsPreview - PDF (436 KB)
Applications of Wasserstein Distance in Distributionally Robust Optimization
Wang, Ye. University of Southern California. ProQuest Dissertations Publishing, 2018. 11017228.
Abstract/DetailsPreview - PDF (886 KB)
Shape space in terms of wasserstein geometry and application to quantum physics
Lessel, Bernadette. Georg-August-Universitaet Goettingen (Germany). ProQuest Dissertations Publishing, 2018. 13867439.
2018 27
Learning and inference with Wasserstein metricsAuthors:Charles Frogner, Massachusetts Institute of Technology
Abstract:This thesis develops new approaches for three problems in machine learning, using tools from the study of optimal transport (or Wasserstein) distances between probability distributions. Optimal transport distances capture an intuitive notion of similarity between distributions, by incorporating the underlying geometry of the domain of the distributions. Despite their intuitive appeal, optimal transport distances are often difficult to apply in practice, as computing them requires solving a costly optimization problem. In each setting studied here, we describe a numerical method that overcomes this computational bottleneck and enables scaling to real data. In the first part, we consider the problem of multi-output learning in the presence of a metric on the output domain. We develop a loss function that measures the Wasserstein distance between the prediction and ground truth, and describe an efficient learning algorithm based on entropic regularization of the optimal transport problem. We additionally propose a novel extension of the Wasserstein distance from probability measures to unnormalized measures, which is applicable in settings where the ground truth is not naturally expressed as a probability distribution. We show statistical learning bounds for both the Wasserstein loss and its unnormalized counterpart. The Wasserstein loss can encourage smoothness of the predictions with respect to a chosen metric on the output space. We demonstrate this property on a real-data image tagging problem, outperforming a baseline that doesn't use the metric. In the second part, we consider the probabilistic inference problem for diffusion processes. Such processes model a variety of stochastic phenomena and appear often in continuous-time state space models. Exact inference for diffusion processes is generally intractable. In this work, we describe a novel approximate inference method, which is based on a characterization of the diffusion as following a gradient flow in a space of probability densities endowed with a Wasserstein metric. Existing methods for computing this Wasserstein gradient flow rely on discretizing the underlying domain of the diffusion, prohibiting their application to problems in more than several dimensions. In the current work, we propose a novel algorithm for computing a Wasserstein gradient flow that operates directly in a space of continuous functions, free of any underlying mesh. We apply our approximate gradient flow to the problem of filtering a diffusion, showing superior performance where standard filters struggle. Finally, we study the ecological inference problem, which is that of reasoning from aggregate measurements of a population to inferences about the individual behaviors of its members. This problem arises often when dealing with data from economics and political sciences, such as when attempting to infer the demographic breakdown of votes for each political party, given only the aggregate demographic and vote counts separately. Ecological inference is generally ill-posed, and requires prior information to distinguish a unique solution. We propose a novel, general framework for ecological inference that allows for a variety of priors and enables efficient computation of the most probable solution. Unlike previous methods, which rely on Monte Carlo estimates of the posterior, our inference procedure uses an efficient fixed point iteration that is linearly convergent. Given suitable prior information, our method can achieve more accurate inferences than existing methods. We additionally explore a sampling algorithm for estimating credible regionsShow more
Thesis, Dissertation, 2018
English
Publisher:2018
2018 28
Generative modeling using the sliced Wasserstein distanceAuthor:Ishan Deshpande
Summary:Generative adversarial nets (GANs) are very successful at modeling distributions from given samples, even in the high-dimensional case. However, their formulation is also known to be hard to optimize and often unstable. While the aforementioned problems are particularly true for early GAN formulations, there has been significant empirically motivated and theoretically founded progress to improve stability, for instance, by using the Wasserstein distance rather than the Jenson-Shannon divergence. Here, we consider an alternative formulation for generative modeling based on random projections which, in its simplest form, results in a single objective rather than a saddlepoint formulation. By augmenting this approach with a discriminator we improve its accuracy. We found our approach to be significantly more stable compared to even the improved Wasserstein GAN. Further, unlike the traditional GAN loss, the loss formulated in our method is a good measure of the actual distance between the distributions and, for the first time for GAN training, we are able to show estimates for the sameShow more
Thesis, Dissertation, 2018
English
Publisher:University of Illinois at Urbana-Champaign, Urbana, Ill., 2018
3018 29 thesis
Image and video compression using deep networkAuthors:Nayan Singhal (Author), Philipp Krähenbühl (Degree supervisor)
Abstract:A large fraction of internet traffic revolves around the image and video transfers. All the moments, memories, and experiences that we share online are heavily dependent on strong image and video compression. Strong compression techniques significantly reduce the cost of transmission and storage. Traditional image and video compression techniques are laboriously hand-designed and hand-optimized, and thus become less efficient for current needs. In this work, we explore a series of image and video compression architectures to improve the performance of compression. On the image compression side, we explore the model that integrates auto-encoder and GANs. The results show that WGAN performs better among all the models we tried and is worth exploring in the deep video codec. On the video compression side, our model is based on Wu et al. [43] and [19]. We formulate the video compression problem as a joint rate-distortion optimization problem. This helps us to efficiently throw out a lot of information from the bottleneck layer and achieve good performance with lower bit-rates. Our deep video codec outperforms todays prevailing distance models by Wu et al. on Kinetics dataset in terms of PSNR. From the results we have on PSNR metrics, we believe that we can achieve a significantly better performance in video compressionShow more
Thesis, Dissertation, 2018
English
2018 30 thesis
Problemas de clasificación : una perspectiva robusta con la métrica de Wasserstein
Authors:Jorge Andrés Acosta Melo, Mauricio José Junca Peláez
Summary:El objetivo central de este trabajo es dar un contexto a los problemas de clasificación para los casos de máquinas de soporte vectorial y regresión logística. La idea central es abordar estos problemas con un enfoque robusto con ayuda de la métrica de Wasserstein que se define en el espacio de medidas de probabilidad de un espacio muestral dado. Luego, se proporciona un planteamiento equivalente y su justificación para hacer el problema robusto distribucionalmente, un problema con implementación computacional al obtener una expresión del problema inicial en el ámbito de problemas de optimización convexa con finitas restricciones. Para cumplir con este ambicioso objetivo hay que hacer un estudio relativamente minucioso en propiedades de funciones convexas, la métrica de Wasserstein, problemas cónicos lineales y el teorema de dualidad y sus distintas versiones en distintos contextosShow more
Thesis, Dissertation, 2018
Spanish
Publisher:Uniandes, Bogotá, 2018
2018 31 thesis
基於最佳化傳輸之對抗式領域調適 = Wasserstein Adversarial Domain Adaptation / Ji yu zui jia hua chuan shu zhi dui kang shi ling yu diao shi = Wasserstein Adversarial Domain AdaptationShow more
Authors:呂昱穎著 ; 簡仁宗指導, 呂昱穎, 著, Yu-Ying Lyu, Jen-Tzung Chien, 簡仁宗 / lu yu ying zhu ; jian ren zong zhi dao, Luyuying, Jianrenzong
Thesis, Dissertation, 2018[min 107]
English, Chu ban
Publisher:國立交通大學, Xin zhu shi, 2018[min 107]
2018 32 thesis see 2020 11
Optimización robusta distribucional con métrica de Wasserstein y algunas aplicaciones
Authors:Diego Fernando Fonseca Valero, Mauricio José Junca Peláez
Summary:En el presente trabajo estudiaremos los problemas de Optimización Robusta Distribucional DRO, estos son problemas de optimización estocástica formulados desde una visión robusta, esta visión consiste en asumir que la distribución verdadera de la variable aleatoria involucrada en el problema pertenece a un conjunto de distribuciones llamado conjunto de ambigüedad, para este caso tal conjunto se define usando la métrica de Wasserstein. Asumiendo ciertas condiciones en la función objetivo, menos restrictivas que las impuestas hasta ahora en la literatura, demostraremos que un DRO de este tipo se puede reformular como un problema de optimización semi-infinita y que dependiendo de la función objetivo dicho problema se puede formular como un problema de optimización convexa finito. Por último presentaremos una serie de aplicaciones en campos como la estadística y la economía, estas aplicaciones son todas contribuciones propias de este trabajoShow more
Thesis, Dissertation, 2018
Spanish
Publisher:Uniandes, Bogotá, 2018
<–– 67 before 2018
+ 32 titles in 2018
= 99 toll 2018
end 2018
start 2019
2019 1
|
Diffusive processes on the Wasserstein space: Coalescing models, Regularization properties and
by Marx, Victor
Université Côte d'Azur, 2019
The aim of this thesis is to study a class of diffusive stochastic processes with values in the space of probability measures on the real line, called...
Dissertation/ThesisCitation Online
2019 2
|
Diffusive processes on the Wasserstein space : coalescing models, regularization properties and...
by Marx, Victor
École doctorale Sciences fondamentales et appliquées (Nice), 2019
The aim of this thesis is to study a class of diffusive stochastic processes with values in the space of probability measures on the real line, called...
Dissertation/ThesisCitation Online
2019 3
Wasserstein Generative Adversarial Network based De-Blurring using Perceptual Similarity
by Minsoo Hong
2019
De-blurring from blurred image is a one of important image processing method and it can be used for pre-processing step in many multimedia and computer vision...
Dissertation/ThesisCitation Online
Preview
Cite this item Email this item Save this item More actions
2019 4
OPEN ACCESS
Reproducing-kernel Hilbert space regression with notes on the Wasserstein distance
by Page, Stephen
Lancaster University, 2019
We study kernel least-squares estimators for the regression problem subject to a norm constraint. We bound the squared L2 error of our estimators with respect...
Dissertation/ThesisCitation Online
MR4197822 Thesis Page, Stephen; Reproducing-Kernel Hilbert Space Regression with Notes on the Wasserstein Distance. Thesis (Ph.D.)–Lancaster University (United Kingdom). 2019. 276 pp. ISBN: 979-8691-27223-3, ProQuest LLC
2019 5
Optimal control in Wasserstein spaces
by Bonnet, Benoît
2019
Une vaste quantité d'outils mathématiques permettant la modélisation et l'analyse des problèmes multi-agents ont récemment été développés dans le cadre de la...
|
2019 6
2019 9
Lebrat, Léo. Projection au sens de Wasserstein 2 sur des espaces structurés de mesures : Projection in the 2-Wasserstein sense on structured measure space.
Degree: Docteur es, Mathématiques Appliquées, 2019, Toulouse, INSA
URL: http://www.theses.fr/2019ISAT0035
Cette thèse s’intéresse à l’approximation pour la métrique de 2-Wasserstein de mesures de probabilité par une mesure structurée. Les mesures structurées étudiées sont des discrétisations… (more)
Subjects/Keywords: Distance de Wasserstein; Optimisation; Théorie de la mesure; Théorie de l’échantillonnage; Blue noise; Projection de courbes; Quantification; Transport optimal; Diagramme de Laguerre; Wasserstein distance; Optimization; Measure theory; Sampling theory; Blue noise; Curve projection; Quantization; Optimal transport; Power diagrams; 519
Record Details Similar Records Cite Share »
2019 10
Algorithms for optimal transport and wasserstein distances
by Schrieber, Jörn
Dissertation/Thesis: Citation Online
Algorithms for Optimal Transport and Wasserstein Distances .
Feb 28, 2019 - Algorithms for Optimal Transport and Wasserstein Distances. Schrieber, Jörn. Doctoral thesis. Date of Examination: 2019-02-14. Date of issue: ...
Schrieber, Jörn. Algorithms for Optimal Transport and Wasserstein Distances.
Degree: PhD, Mathematik und Informatik, 2019, Georg-August-Universität Göttingen
URL: http://hdl.handle.net/11858/00-1735-0000-002E-E5B2-B
► Optimal Transport and Wasserstein Distance are closely related terms that do not only have a long history in the mathematical literature, but also have seen… (more)
Record Details Similar Records Cite Share »
Boston University
2019 11
Structure preserving discretization and approximation of gradient flows in Wasserstein-like spaces
by Plazotta, Simon Dissertation/Thesis: Citation Online
Structure preserving discretization and approximation of ...
by SJ Plazotta - 2019
thesis is to investigate structure-preserving, tempo- ral semi-discretizations and approximations for PDEs with gradient flow structure with the particular application to evolution problems in the space of probability measures equipped with the L2-Wasserstein distance.
Publisher:Universitätsbibliothek der TU München, München, 2019
2019 12
Courbes et applications optimales à valeurs dans l'espace de Wasserstein
by Lavenant, Hugo
L'espace de Wasserstein est l'ensemble des mesures de probabilité définies sur un domaine fixé et muni de la distance de Wasserstein quadratique. Dans ce...
Dissertation/Thesis: Full Text Online
[French Statistical properties of the barycenter in Wasserstein space]
PDF] Courbes et applications optimales à valeurs dans l'espace de ...
by H Lavenant - 2019 - Related articles
Jun 3, 2019 - 1.1 Optimal transport and Wasserstein distances: a brief historical survey . ..... A.2 Courbes optimales à valeurs dans l'espace de Wasserstein .
Lavenant, Hugo. Courbes et applications optimales à valeurs dans l'espace de Wasserstein : Optimal curves and mappings valued in the Wasserstein space.
Degree: Docteur es, Mathématiques fondamentales, 2019, Université Paris-Saclay (ComUE)
URL: http://www.theses.fr/2019SACLS112
L'espace de Wasserstein est l'ensemble des mesures de probabilité définies sur un domaine fixé et muni de la distance de Wasserstein quadratique. Dans ce travail,… (more)
Subjects/Keywords: Calcul des variations; Transport optimal; Régularité elliptique; Analyse dans les espaces métriques; Calculus of variations; Optimal transport; Elliptic regularity; Analysis in metric spaces
Record Details Similar Records Cite Share »
2019 13
The generalized Vaserstein symbol
by Syed, Tariq 2019
Dissertation/Thesis: Citation Online
The Generalized Vaserstein Symbol - Tariq Syed - Google Books
München, 2019
PhD, Mathematik, Informatik und Statistik
Syed
2019 14
Algorithms for Optimal Transport and Wasserstein Distances
books.google.com › books
Jörn Schrieber - 2019 - Dissertation Göttingen
Optimal Transport and Wasserstein Distance are closely related terms that do not only have a long history in the mathematical literature, but also have seen a resurgence in recent years, particularly in the context of the many applications ...
Publisher:Niedersächsische Staats- und Universitätsbibliothek Göttingen, Göttingen, 2019
2019 15
Distributionally Robust Learning Under the Wasserstein Metric
by R Chen - 2019 -Boston U Related articles
The remainder of this dissertation is organized as follows. In Chapter 2, we develop the Wasserstein DRO formulation for linear regression under absolute error ...
Distributionally Robust Learning under the Wasserstein Metric
by R Chen - 2019 - Related articles
This dissertation develops a comprehensive statistical learning framework that is robust to (distributional) perturbations in the data using Distributionally Robust ...
8. Chen, Ruidi. Distributionally Robust Learning under the Wasserstein Metric.
Degree: PhD, Systems Engineering, 2019, Boston University
URL: http://hdl.handle.net/2144/38236
► This dissertation develops a comprehensive statistical learning framework that is robust to (distributional) perturbations in the data using Distributionally Robust Optimization (DRO) under the Wasserstein… (more)
Subjects/Keywords: Statistics; Distributionally robust optimization; Grouped variable selection; Health informatics; Multivariate linear regression; Regression; Classification; Wasserstein metric
Record Details Similar Records Cite Share »
Georg-August-Universität Göttingen
MR4051515 Thesis Chen, Ruidi Distributionally Robust Learning Under the Wasserstein Metric. Thesis (Ph.D.)–Boston University. 2019. 206 pp. ISBN: 978-1687-99234-5, ProQuest LLC
2019 16
Wasserstein Generative Adversarial Privacy Networks
essay.utwente.nl › Mulder_MA_EEMCS
PDF University of Twente
by K Mulder - 2019 - Related articles
Jul 19, 2019 - In this thesis, we consider whether we can modify the approach taken by [1] to use a Wasserstein GAN as basis instead of a traditional GAN, in ...
2019 17
Deep generative models via explicit Wasserstein minimization
www.ideals.illinois.edu › handle
by Y Chen - 2019 - Related articles
Aug 23, 2019 - This thesis provides a procedure to fit generative networks to target distributions, with the goal of a small Wasserstein distance (or other optimal ...
University of Illinois at Urbana-Champaign MS
Chen, Yucheng. Deep generative models via explicit Wasserstein minimization.
Degree: MS, Computer Science, 2019, University of Illinois – Urbana-Champaign
URL: http://hdl.handle.net/2142/104932
► This thesis provides a procedure to fit generative networks to target distributions, with the goal of a small Wasserstein distance (or other optimal transport costs).… (more)
Subjects/Keywords: Deep Generative Models; Generative Adversarial Networks; Optimal Transport
…not exactly minimize the Wasserstein distance [6, 7, 8, 9]. The procedure also… …simple generator, promising empirical results measuring Wasserstein distance to a test set… …variety of theoretical guarantees Foremost amongst these are showing that the Wasserstein… …property can be proved via the triangle inequality for Wasserstein distances, however such an… …approach introduces the Wasserstein distance between ν and ν̂, namely W (ν, ν̂), which…
Record Details Similar Records Cite Share »
2019 18
Optimal Control in Wasserstein Spaces
Nov 19, 2019 - Download Citation | Optimal Control in Wasserstein Spaces | A ... In this thesis, we extend for the first time several of these concepts to the ...
bymBonnet, Benoît
Aix-Marseille Universite, 2019
A wealth of mathematical tools allowing to model and analyse multi-agent systems has been brought forth as a consequence of recent developments in optimal...
2019 19
Masters Thesis - TU Delft Repositories
repository.tudelft.nl › islandora › object › datastream › OBJ › download
PDF Delf 2019
the Wasserstein Metric in Deep. Reinforcement Learning. The regularizing effect of modelling return distributions. Master of Science Thesis. For the degree of ...
2019 20
Prioritized Experience Replay based on the Wasserstein Metric in Deep Reinforcement Learning
Apr 12, 2019 - Prioritized Experience Replay based on the Wasserstein Metric in Deep Reinforcement Learning: The regularizing effect of modelling return ...
The regularizing effect of modelling return distributions
Master of Science Thesis Delft TU
For the degree of Master of Science in Systems and Control at Delft University of Technology
T. Greevink April 5, 2019
2019 21
1. Syed, Tariq. The generalized Vaserstein symbol.
Degree: PhD, Mathematik, Informatik und Statistik, 2019, Ludwig-Maximilians-Universität
URL: https://edoc.ub.uni-muenchen.de/24359/
Record Details Similar Records Cite Share »
2019 22
Marx, Victor. Processus de diffusion sur l’espace de Wasserstein : modèles coalescents, propriétés de régularisation et équations de McKean-Vlasov : Diffusive processes on the Wasserstein space : coalescing models, regularization properties and McKean-Vlasov equations.
Degree: Docteur es, Mathématiques, 2019, Université Côte d'Azur (ComUE)
URL: http://www.theses.fr/2019AZUR4065
► La thèse vise à étudier une classe de processus stochastiques à valeurs dans l’espace des mesures de probabilité sur la droite réelle, appelé espace de… (more)
Subjects/Keywords: Diffusion de Wasserstein; Système de particules en interaction; Particules coalescentes; Propriétés de régularisation; Équation de McKean-Vlasov; Équation de Fokker-Planck; Restauration de l'unicité; Notion de solution faible; Formule de Bismut-Elworthy; Wasserstein diffusion; Interacting particle system; Coalescing particles; Regularization properties; McKean-Vlasov equation; Fokker-Planck equation; Restoration of uniqueness; Notion of weak solution; Bismut-Elworthy formula
Record Details Similar Records Cite Share »
2019 23
Projection au sens de Wasserstein 2 sur des espaces structurés de mesures
by Lebrat, Léo
Cette thèse s’intéresse à l’approximation pour la métrique de 2-Wasserstein de mesures de probabilité par une mesure structurée. Les mesures structurées...
2019 24
thesis exam 2019
Diffusions on Wasserstein Spaces - bonndoc - Universität Bonn
bonndoc.ulb.uni-bonn.de › xmlui › handle
05.05.2020 ... Dello Schiavo, Lorenzo: Diffusions on Wasserstein Spaces. - Bonn, 2020. - Dissertation, Rheinische Friedrich-Wilhelms-Universität Bonn.
by L Dello Schiavo · 2020 · Related articles
2019 25
Calendar | Dean of Students - Boston University
Jun 12, 2020 — The learning problems that are studied in this dissertation include: (i) Distributionally Robust Linear ... over a probabilistic ambiguity set characterized by the Wasserstein metric; (ii) Groupwise Wasserstein ... June 25, 2020.
2019 26
Distributionally Robust Learning Under the Wasserstein Metric
by Chen, Ruidi
This dissertation develops a comprehensive statistical learning framework that is robust to (distributional) perturbations in the data using Distributionally...
Dissertation/ThesisFull Text Online
2019 27
Wasserstein Generative Adversarial Network based De-Blurring using Perceptual Similarity
by Minsoo Hong
De-blurring from blurred image is a one of important image processing method and it can be used for pre-processing step in many multimedia and computer vision...
Dissertation/ThesisCitation Online
2019 28
Open Access
Reproducing-kernel Hilbert space regression with notes on the Wasserstein distance
by Page, Stephen
Lancaster University, 2019
We study kernel least-squares estimators for the regression problem subject to a norm constraint. We bound the squared L2 error of our estimators with respect...
Dissertation/ThesisCitation Online
2019 29
Open Access
Optimal curves and mappings valued in the Wasserstein space
by Lavenant, Hugo
École doctorale de mathématiques Hadamard (Orsay, Essonne ; 2015-....), 2019
The Wasserstein space is the space of probability measures over a given domain endowed with the quadratic Wasserstein distance. In this work, we study...
Dissertation/ThesisCitation Online
2019 30
by Ramesh, Chandini RIT
Generative Adversarial Networks (GANs) provide a fascinating new paradigm in machine learning and artificial intelligence, especially in the context of...
Dissertation/ThesisCitation Online
Relaxed Wasserstein, Generative Adversarial Networks, Variational Autoencoders and Their Applications
Yang, Nan. University of California, Berkeley, ProQuest Dissertations Publishing, 2019. 22620074.
Abstract/DetailsPreview - PDF (742 KB)
Reproducing-Kernel Hilbert Space Regression with Notes on the Wasserstein Distance
Page, Stephen. Lancaster University (United Kingdom). ProQuest Dissertations Publishing, 2019. 28277860.
Abstract/DetailsPreview - PDF (401 KB)
2019 33
Algorithms for optimal transport and wasserstein distances
Schrieber, Jörn. Georg-August-Universitaet Goettingen (Germany). ProQuest Dissertations Publishing, 2019. 13888207.
2019 34 onnine
Study on K-meap Clustering and Wasserstein GAN for Distributional-valued Variable of IoT
by 吳致緯;
WU, JHI-WEI
碩士 國立虎尾科技大學 資訊工程系碩士班 107
Dissertation/ThesisCitation Online
2019 35
Optimal Transport for Machine Learning - Rémi Flamary
remi.flamary.com › biblio › hdr
by R FLAMARY · 2019 — Habilitation à Diriger des Recherches ... 5 Optimal Transport between empirical distributions ... end we extended the Gromov-Wasserstein distance [Vayer 2018,Vayer 2019a] ... E. Decencière, R. Flamary, R. Gavazzi, others, The Strong Gravitational Lens Finding ... Sharp asymptotic and finite-sample rates of convergence.
2019 36
MR4051515 Thesis Chen, Ruidi Distributionally Robust Learning Under the Wasserstein Metric. Thesis (Ph.D.)–Boston University. 2019. 206 pp. ISBN: 978-1687-99234-5, ProQuest LLC
Review PDF Clipboard Series Thesis
2019 37 master
L STRACCA - 2019 - etd.adm.unipi.it
Un problema inverso ha come scopo la determinazione o la stima dei parametri incogniti di
un modello, conoscendo i dati da esso generati e l'operatore di forward modelling che
descrive la relazione tra un modello generico e il rispettivo dato predetto. In un qualunque …
2019 38 online OPEN ACCESS
Relaxed Wasserstein, Generative Adversarial Networks, Variational Autoencoders and their...
by Yang, Nan
Statistical divergences play an important role in many data-driven applications. Two notable examples are Distributionally Robust Optimization (DRO) problems...
Dissertation/ThesisFull Text Online
2019 39 online OPEN ACCESS
by Marx, Victor
La thèse vise à étudier une classe de processus stochastiques à valeurs dans l’espace des mesures de probabilité sur la droite réelle, appelé espace de...
Dissertation/ThesisFull Text Online
2019 40
Dissertation or Thesis Preview Available
Reroducing-Kernel Hilbert Space Regression with Notes on the Wasserstein Distance
Page, Stephen.Lancaster University (United Kingdom). ProQuest Dissertations Publishing, 2019. 28277860.
Abstract/DetailsPreview - PDF (401 KB)
219 41
Dissertation or Thesis Citation
Structure preserving discretization and approximation of gradient flows in Wasserstein-like space
Alternate title: Strukturerhaltende Diskretisierungen und Approximationen von Gradienten Flüssen in Wasserstein ähnlichen Räumen
Plazotta, Simon.Technische Universitaet Muenchen (Germany). ProQuest Dissertations Publishing, 2019. 27552212.
Details Show More
2019 42
A使用WGAN-GP對臉部馬賽克進行眼睛補圖 = Eye In-painting Using WGAN-GP for Face Images with Mosaic / Shi yongWGAN-GP dui lian bu ma sai ke jin xing yan jing bu tu = Eye In-painting Using WGAN-GP for Face Images with Mosaic
Authors:吳承軒, 著, H. T. Chang, Cheng Hsuan Wu, 張賢宗 / Chengxuan Wu, Xianzong Zhang
Thesis, Dissertation, 2019[min 108]
Chinese, Chu ban
Publisher:長庚大學, Tao yuan shi, 2019[min 108]
2019 43 thesis
A comparative assessment of the impact of various norms on Wasserstein generative adversarial networks
Author:Chandini Ramesh (Author)
Abstract:"Generative Adversarial Networks (GANs) provide a fascinating new paradigm in machine learning and artificial intelligence, especially in the context of unsupervised learning. GANs are quickly becoming a state of the art tool, used in various applications such as image generation, image super resolutions, text generation, text to image synthesis to name a few. However, GANs potential is restricted due to the various training difficulties. To overcome the training difficulties of GANs, the use of a more powerful measure of dissimilarity via the use of the Wasserstein distance was proposed. Thereby giving birth to the GAN extension known as Wasserstein Generative Adversarial Networks (WGANs). Recognizing the crucial and central role played by both the cost function and the order of the Wasserstein distance used in WGAN, this thesis seeks to provide a comparative assessment of the effect of a various common used norms on WGANs. Inspired by the impact of norms like the L1-norm in LASSO Regression, the L2-norm Ridge Regression and the great success of the combination of the L1 and L2 norms in elastic net and its extensions in statistical machine learning, we consider exploring and investigating to a relatively large extent, the effect of these very same norms in the WGAN context. In this thesis, the primary goal of our research is to study the impact of these norms on WGANs from a pure computational and empirical standpoint, with an emphasis on how each norm impacts the space of the weights/parameters of the machines contributing to the WGAN. We also explore the effect of different clipping values which are used to enforce the k-Lipschitz constraint on the functions making up the specific WGAN under consideration. Another crucial component of the research carried out in this thesis focuses on the impact of the number of training iterations on the WGAN loss function (objective function) which somehow gives us an empirical rough estimate of the computational complexity of WGANs. Finally, and quite importantly, in keeping WGANs' application to recovery of scenes and reconstruction of complex images, we dedicate a relative important part of our research to the comparison of the quality of recovery across various choices of the norms considered. Like previous researchers before us, we perform a substantial empirical exploration on both synthetic data and real life data. We specifically explore a simulated data set made up of a mixture of eight bivariate Gaussian random variables with large gaps, the likes of which would be hard task for traditional GANs but can be readily handled quite well be WGANs thanks to the inherent strength/power of the underlying Wasserstein distance. We also explore various real data sets, namely the ubiquitous MNIST datasets made up of handwritten digits and the now very popular CIFAR-10 dataset used an de facto accepted benchmark data set for GANs and WGANs. For all the datasets, synthetic and real, we provide a thorough comparative assessment of the effect and impact of the norms mentioned earlier, and it can be readily observed that there are indeed qualitative and quantitative difference from one norm to another, with differences established via measures such as (a) shape, value and pattern of the generator loss, (b) shape, value and pattern of the discriminator loss (c) shape, value and pattern of the inception score, and (d) human inspection of quality of recovery or reconstruction of images and scenes."--Abstract
Show more
Thesis, Dissertation, 2019
English
Publisher:Rochester Institute of Technology, Rochester, NY, 2019
2019 44 thesis
結合Wasserstein Distance於對抗領域適應之研究 = A generative adversarial network in domain adaptation by utilizing the wasserstein distance / Jie heWasserstein Distance yu dui kang ling yu shi ying zhi yan jiu = A generative adversarial network in domain adaptation by utilizing the wasserstein distance
Show more
2019 thesis
Authors:許維哲撰., 許維哲, 劉立頌 / xu wei zhe zhuan, Weizhe Xu, Lisong Liu
Thesis, Dissertation, min 108[2019]
Chinese
Publisher:許維哲, Jia yi xian, min 108[2019]
2019 45 thesis
Distribuciones de máxima entropía en bolas de Wasserstein
Authors:Luis Felipe Vargas Beltrán, Mauricio Fernando Velasco Gregory, Adolfo José Quiroz Salazar, Fabrice Gamboa
Summary:"Presentamos un método para hallar la distribución de máxima entropía en la Bola de Wasserstein de un radio dado t centrada en la distribución empírica dada por n puntos. Esta distribución es la más general (minimiza la cantidad de información previa) a una distancia $t$ de la distribución empírica y de aquí su importancia en inferencia estadística. El método depende de un nuevo algoritmo de cutting plane y es generalizado a otro tipo de funciones, entre ellas los Funcionales Euclidianos Subaditivos. También, damos una nueva generalización al algoritmo de Fortune para generar el diagrama de Voronoi Pesado Aditivamente que permite hacer optimización en Bolas de Wasserstein a mayor velocidad." -- Tomado del Formato de Documento de Grado
Show more
Thesis, Dissertation, 2019
Spanish
2019 46 thesis
Structure preserving discretization and approximation of gradient flows in Wasserstein-like space
Authors:Simon Plazotta, Daniel Matthes, Giuseppe Savaré
Thesis, Dissertation, 2019
English
Publisher:Universitätsbibliothek der TU München, München, 2019
<–– 99 tittles before 2019
+ 46 in 2019
= 145 titles till 2019
end 2019
start 2020
2020 1
Open Access
by Wu, Jiqing
Dissertation/ThesisCitation Online
2020 2
Lian, Xin. Unsupervised Multilingual Alignment using Wasserstein Barycenter.
Degree: 2020, University of Waterloo
URL: http://hdl.handle.net/10012/15557
► We investigate the language alignment problem when there are multiple languages, and we are interested in finding translation between all pairs of languages. The problem… (more)
Record Details Similar Records Cite Share »
University of Illinois – Urbana-Champaign
2020 3
by Chen, Yukun; Wang, James Z
2020 Penn State University
In the past decade, fueled by the rapid advances of big data technology and machine learning algorithms, data science has become a new paradigm of science and...
Dissertation/Thesis
ONLINE, Electronic thesis, ONLINE
Aggregated Wasserstein distance for hidden Markov models and automated morphological
2020 4
Wu, Jiqing. Improving Wasserstein Generative Models for Image Synthesis and Enhancement.
Degree: 2020, ETH Zürich
URL: http://hdl.handle.net/20.500.11850/414485
Subjects/Keywords: info:eu-repo/classification/ddc/004; Data processing, computer science
2020 5
Classification of Atomic Environments Via the Gromov-Wasserstein Distance
by Kawano, Sakura, M.S. University of California, Davis. 2020: 62 pages; 27998403.
2020 6
MR4157964 Thesis Mirth, Joshua Robert; Vietoris—Rips Metric Thickenings and Wasserstein Spaces. Thesis (Ph.D.)–Colorado State University. 2020. 107 pp. ISBN: 979-8664-76221-1, ProQuest LLC
Colorado State University
4. Mirth, Joshua. Vietoris–Rips metric thickenings and Wasserstein spaces.
Degree: PhD, Mathematics, 2020, Colorado State University
URL: http://hdl.handle.net/10217/211767
► If the vertex set, X, of a simplicial complex, K, is a metric space, then K can be interpreted as a subset of the Wasserstein… (more)
Subjects/Keywords: optimal transport; Vietoris–Rips complex; category theory; Wasserstein space; topology
DISSERTATION VIETORIS–RIPS METRIC THICKENINGS ...
2020 7
[PDF] Nonparametric Density Estimation with Wasserstein Distance for Actuarial Applications
EG Luini - iris.uniroma1.it
Density estimation is a central topic in statistics and a fundamental task of actuarial sciences. In this work, we present an algorithm for approximating multivariate empirical densities with a piecewise constant distribution defined on a hyperrectangular-shaped partition of the domain. The piecewise constant distribution is constructed through a hierarchical bisection scheme, such that locally, the sample cannot be statistically distinguished from a uniform distribution. The Wasserstein distance represents the basic element of the bisection …
Related articles All 2 versions View as HTML
Showing the best result for this search. See all results
2020 8
Wasserstein barycenters : statistics and optimization
Thesis: S.M., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, May, 2020. Cataloged from the official PDF of ...
by AJ Stromme · 2020 MIT
2020 9
Asset Allocation in ... - Erasmus University Thesis Repository
Asset Allocation in Emerging Market Space using Wasserstein Generative Adversarial Networks
Bakx, A. 2020-07-14. Asset Allocation in Emerging Market Space using Wasserstein Generative Adversarial Networks ... Thesis Advisor, Vermeulen, S.H.L.C.G..Erasmus School of Economics Bakx, A.
2020 10
WGAIN: Data Imputation using Wasserstein GAIN/submitted ...
The goal of this thesis was to proof that it is possible to use the GAIN algorithm together with the Wasserstein setting and apply it to impute missing values. Another ...
by C Halmich · 2020
2020 11
Wasserstein Distributionally Robust Learning - Infoscience
Jun 8, 2020 — In the final part of the thesis we study a distributionally robust mean square error estimation problem over a nonconvex Wasserstein ambiguity ...
by S Shafieezadeh Abadeh · 2020
Lausanne, EPFL
2020 12
Distributional Sliced-Wasserstein and Applications to ... - arXiv
particular Wasserstein distance in practical applications. Recently, several numerical methods have ... ML] 18 Feb 2020 ... PhD thesis, Paris 11, 2013. Bunne, C.
by K Nguyen · 2020 · Cited by 2 · Related articles
2020 13
Optimización robusta distribucional con métrica de Wasserstein y algunas aplicaciones
Optimización robusta distribucional con métrica de Wasserstein y algunas aplicaciones. RIS Mendeley. URI: http://hdl.handle.net/1992/34569.
by DF Fonseca Valero
master thesis 2020
2020 14
Classification of Atomic Environments Via the Gromov-Wasserstein Distance
Kawano, Sakura. University of California, Davis, ProQuest Dissertations Publishing, 2020. 27998403.
2020 15
An enhanced uncertainty principle for the Vaserstein distance
Carroll, Tom; Massaneda, Xavier; Ortega-Cerdà, Joaquim. arXiv.org; Ithaca, Oct 8, 2020.
Get full text
Link to external site, this link will open in a new window
Show Abstract
2020 16
Студент ПМИ нашел оптимальный алгоритм решения ...
Sep 30, 2020 — Защита кандидатской диссертации Соколовой Анны Ильиничны ... Поиск барицентра Вассерштейна — это не самая известная задача ...
Студент ПМИ нашел оптимальный алгоритм решения задачи поиска барицентра Вассерштейна
[Russian Student at GMI found optimal algorithm for solution of Wasserstein bariocenter search problem ]
2020 17
Joshua Mirth Ph.D. Colorado State University 2020
Dissertation: Vietoris-Rips metric thickenings and Wasserstein spaces
Mathematics Subject Classification: 55—Algebraic topology
MR4157964 Thesis
Mirth, Joshua Robert
Vietoris—Rips Metric Thickenings and Wasserstein Spaces.
Thesis (Ph.D.)–Colorado State University. 2020. 107 pp. ISBN: 979-8664-76221-1
2020 18
Wu, Kaiwen. Wasserstein Adversarial Robustness.
Degree: 2020, University of Waterloo
URL: http://hdl.handle.net/10012/16345
► Deep models, while being extremely flexible and accurate, are surprisingly vulnerable to ``small, imperceptible'' perturbations known as adversarial attacks. While the majority of existing attacks… (more)
Subjects/Keywords: Wasserstein distance; adversarial robustness; optimization
Record Details Similar Records Cite Share »
Colorado State University
2020 19
Unsupervised Multilingual Alignment using Wasserstein Barycenter
by Lian, Xin
We investigate the language alignment problem when there are multiple languages, and we are interested in finding translation between all pairs of languages....
Dissertation/ThesisCitation Online
2020 20
Aggregated Wasserstein distance for hidden Markov models and automated morphological characterization...
by Chen, Yukun; Wang, James Z
MR4327033 Thesis Chen, Yukun; Aggregated Wasserstein Distance for Hidden Markov Models and Automated Morphological Characterization of Placenta from Photos. Thesis (Ph.D.)–The Pennsylvania State University. 2020. 135 pp. ISBN: 979-8535-58610-6, ProQuest LLC
2020 21
In the past decade, fueled by the rapid advances of big data technology and machine learning algorithms, data science has become a new paradigm of science and...
Dissertation/Thesis
Check Availability
2020 22
Wasserstein Adversarial Robustness
by Wu, Kaiwen
2020
Deep models, while being extremely flexible and accurate, are surprisingly vulnerable to ``small, imperceptible'' perturbations known as adversarial attacks....
Dissertation/ThesisCitation Online
2020 23
Improving Wasserstein Generative Models for Image Synthesis and Enhancement
by Wu, Jiqing
2020 Dissertation/ThesisCitation Online
2020 24
Wasserstein Distributionally Robust Learning
S Shafieezadeh Abadeh - 2020 - infoscience.epfl.ch
… Contributions and Structure of the Thesis This thesis is divided into three self-contained chapters
organized in the chronological … problem over a nonconvex Wasserstein ambiguity set containing
only normal dis- tributions … Wasser- stein distributionally robust Kalman filtering …
2020 25
thesis 2020
Projection Robust Wasserstein Distance and Riemannian ...
Projection robust Wasserstein (PRW) distance, or Wasserstein projection pursuit ... Contribution: In this paper, we study the computation of the PRW distance ... PhD thesis, Ph. D. Dissertation, Dissertation de Mastere, Université College Gublin ...
by T Lin · 2020 · Cited by 2
2020 26
to thesis 2020
E PhD Final Defense of Ruidi Chen - Calendar | Dean of ...
Jun 12, 2020 — The learning problems that are studied in this dissertation include: (i) Distributionally Robust Linear ... over a probabilistic ambiguity set characterized by the Wasserstein metric; (ii) Groupwise Wasserstein ... June 25, 2020.
ITLE: DISTRIBUTIONALLY ROBUST LEARNING UNDER THE WASSERSTEIN METRIC
2020 27
to thesis 2020
arXiv:2006.07458v6 [cs.LG] 20 Dec 2020 - arXiv.org
Dec 20, 2020 — Projection Robust Wasserstein Distance and Riemannian ... [2020] further provided several fundamental statistical bounds for PRW ... PhD thesis, Ph. D. Dissertation, Dissertation de Mastere, Université College Gublin, Irlande ...
by T Lin · 2020 · Cited by 2
2020 28
Projection Robust Wasserstein Distance and Riemannian ...
Projection robust Wasserstein (PRW) distance, or Wasserstein projection pursuit ... Contribution: In this paper, we study the computation of the PRW distance ... PhD thesis, Ph. D. Dissertation, Dissertation de Mastere, Université College Gublin ...
by T Lin · 2020 · Cited by 2
2020 29
E PhD Final Defense of Ruidi Chen - Calendar | Dean of ...
Jun 12, 2020 — The learning problems that are studied in this dissertation include: (i) Distributionally Robust Linear ... over a probabilistic ambiguity set characterized by the Wasserstein metric; (ii) Groupwise Wasserstein ... June 25, 2020.
ITLE: DISTRIBUTIONALLY ROBUST LEARNING UNDER THE WASSERSTEIN METRIC
2020 30
arXiv:2006.07458v6 [cs.LG] 20 Dec 2020 - arXiv.org
Dec 20, 2020 — Projection Robust Wasserstein Distance and Riemannian ... [2020] further provided several fundamental statistical bounds for PRW ... PhD thesis, Ph. D. Dissertation, Dissertation de Mastere, Université College Gublin, Irlande ...
by T Lin · 2020 · Cited by 2
2020 31
Synthetic Data Generation Using Wasserstein Conditional Gans With Gradient Penalty (WCGANS-GP)
M Singh Walia - 2020 - arrow.tudublin.ie
… Dissertations. Title … Disciplines. Computer Sciences. Publication Details. A dissertation submitted in partial fulfilment of the requirements of Technological University Dublin for the degree of M.Sc. in Computer Science (Data Analytics) September 2020. Abstract … book MIT
2020 32
by tromme, Austin J. (Austin James)
Supervised by Philippe Rigollet.
2020 33
2020 34
Wasserstein Adversarial Robustness
by Wu, Kaiwen
Deep models, while being extremely flexible and accurate, are surprisingly vulnerable to ``small, imperceptible'' perturbations known as adversarial attacks....
Dissertation/ThesisCitation Online
2020 35
by Chen, Yukun;
Wang, James Z
In the past decade, fueled by the rapid advances of big data technology and machine learning algorithms, data science has become a new paradigm of science and...
Dissertation/Thesis Check Availability
2020 36
Open Access
Unsupervised Multilingual Alignment using Wasserstein Barycenter
by Lian, Xin
We investigate the language alignment problem when there are multiple languages, and we are interested in finding translation between all pairs of languages....
Dissertation/ThesisCitation Online
2020 37
Open Access
Wasserstein Adversarial Robustness
by Wu, Kaiwen
Deep models, while being extremely flexible and accurate, are surprisingly vulnerable to ``small, imperceptible'' perturbations known as adversarial attacks....
Dissertation/ThesisCitation Online
2020 38
(PDF) The back-and-forth method for Wasserstein gradient flows
www.researchgate.net › publication › 345971036_The_b...
Nov 17, 2020 — We present a method to efficiently compute Wasserstein gradient flows. Our approach is ... Habilitation, Université de Metz,. January 1995. 7.
2020 39
(PDF) Wasserstein Dictionary Learning: Optimal Transport ...
www.researchgate.net › publication › 318981939_Wasser...
Nov 1, 2020 — Further image processing applications are reviewed in the habilitation dissertation. of Papadakis [56]. Wasserstein loss and fidelity. Several ...
2020 40 PDF
THE BACK-AND-FORTH METHOD FOR WASSERSTEIN ...
www.math.ucla.edu › ~majaco › papers › bfm_gf
Oct 24, 2020 — WASSERSTEIN GRADIENT FLOWS ... Abstract. We present a method to efficiently compute Wasserstein ... Habilitation, Université de Metz,.
2020 41 Sept 11
Master's Thesis Presentation • Machine Learning — Wasserstein Adversarial Robustness
cs.uwaterloo.ca › events › masters-thesis-presentation-m...asserstein Autoencoders with Mixture of Gaussian Priors for Stylized Text Generation
Please note: This master's thesis presentation will be given online. Amirpasha Ghabussi ... Variational autoencoders and Wasserstein autoencoders are two widely used methods for text. ... Thursday, January 21, 2021 — 10:00 AM EST ...
Amirpasha Ghabussi, Master’s candidate
David R. Cheriton School of Computer Science
Supervisor: Professor Olga Vechtomova
2020 42
D Singh - 2020 - conservancy.umn.edu
The central theme of this dissertation is stochastic optimization under distributional
ambiguity. One canthink of this as a two player game between a decision maker, who tries to
minimize some loss or maximize some reward, and an adversarial agent that chooses the …
2020 43
Régression quantile extrême : une approche par couplage et ...
https://hal.inria.fr › UMR6623
by B Bobbia · 2020 — Plus précisément, l'estimation de quantiles d'une distribution réelle ... Régression quantile extrême : une approche par couplage et distance de Wasserstein. Benjamin Bobbia 1 ... Université Bourgogne Franche-Comté, 2020.
OPEN ACCESS
Régression quantile extrême : une approche par couplage et distance de Wasserstein
by Bobbia, Benjamin
2020
Ces travaux concernent l'estimation de quantiles extrêmes conditionnels. Plus précisément, l'estimation de quantiles d'une distribution réelle en fonction...
Dissertation/ThesisCitation Online
Preview
Cite this item Email this item Save this item More actions
2020 44
B Ashworth - 2020 - core.ac.uk
There is a growing interest in studying nonlinear partial differential equations which
constitute gradient flows in the Wasserstein metric and related structure preserving
variational discretisations. In this thesis, we focus on the fourth order Derrida-Lebowitz …
Agregated Wasserstein Distance for Hidden Markov Models and Automated Morphological Characterization of Placenta from Photos
Chen, Yukun. The Pennsylvania State University, ProQuest Dissertations Publishing, 2020. 28767292.
Abstract/DetailsPreview - PDF (475 KB)Full text - PDF (23 MB)
Order a copy
2020 46
Data-Driven Distributionally Robust Stochastic Optimization Via Wasserstein Distance with Applications to Portfolio Risk Management and Inventory Control
Singh, Derek R. University of Minnesota. ProQuest Dissertations Publishing, 2020. 28263034.
Abstract/DetailsPreview - PDF (289 KB)Full text - PDF (4 MB)
Vietoris–Rips Metric Thickenings and Wasserstein Spaces
Mirth, Joshua Robert. Colorado State University. ProQuest Dissertations Publishing, 2020. 27995129.
Abstract/DetailsPreview - PDF (796 KB)
Classification of Atomic Environments Via the Gromov-Wasserstein Distance
Kawano, Sakura. University of California, Davis. ProQuest Dissertations Publishing, 2020. 27998403.
Abstract/DetailsPreview - PDF (525 KB)Full text - PDF (1 MB)
2020 49 online OPEN ACCESS
Study of the aggregation procedure : patch fusion and generalized Wasserstein barycenters
by Saint-Dizier, Alexandre
Cette thèse porte sur une classe particulière d'algorithmes de traitement d’images : les méthodes par patchs. Ces méthodes nécessitent une étape appelée...
Dissertation/ThesisFull Text Online
2020 50 online
Aggregated Wasserstein Distance for Hidden Markov Models and Automated Morphological...
by Chen, Yukun
In the past decade, fueled by the rapid advances of big data technology and machine learning algorithms, data science has become a new paradigm of science and...
Dissertation/ThesisFull Text Online
020 51
Self-Supervised Video Object Segmentation using Generative ...
https://upcommons.upc.edu › bitstream › handle
https://upcommons.upc.edu › bitstream › handlePDF
by P Palau Puigdevall · 2020 — A Master Thesis ... In this thesis, we propose a self-supervised ... though the Wasserstein distance results in the same value for both plans, the transport.
2020 52
https://bonndoc.ulb.uni-bonn.de › xmlui › handle
Thirdly, we prove a Rademacher-type result on the Wasserstein space over a closed Riemannian manifold. ... dc.type, Dissertation oder Habilitation.05.05.2020
2020 53
Classification of atomic environments via the Gromov-Wasserstein distanceAuthor:Sakura Kawano (Author)
Summary:Interpreting molecular dynamics simulations usually involves automated classification of local atomic environments to identify regions of interest. Existing approaches are generally limited to a small number of reference structures and only include limited information about the local chemical composition. This work proposes to use a variant of the Gromov-Wasserstein (GW) distance to quantify the difference between a local atomic environment and a set of arbitrary reference environments in a way that is sensitive to atomic displacements, missing atoms, and differences in chemical composition. This involves describing a local atomic environment as a finite metric measure space, which has the additional advantages of not requiring the local environment to be centered on an atom and of not making any assumptions about the material class. Numerical examples illustrate the efficacy and versatility of the algorithmShow mor
Thesis, Dissertation, 2020
English
Publisher:University of California, Davis, Davis, Calif., 2020
2020 54
Wasserstein barycenters : statistics and optimizationAuthors:Austin J. Stromme, Massachusetts Institute of Technology
Abstract:We study a geometric notion of average, the barycenter, over 2-Wasserstein space. We significantly advance the state of the art by introducing extendible geodesics, a simple synthetic geometric condition which implies non-asymptotic convergence of the empirical barycenter in non-negatively curved spaces such as Wasserstein space. We further establish convergence of first-order methods in the Gaussian case, overcoming the nonconvexity of the barycenter functional. These results are accomplished by various novel geometrically inspired estimates for the barycenter functional including a variance inequality, new so-called quantitative stability estimates, and a Polyak-Łojasiewicz (PL) inequality. These inequalities may be of independent interestShow more
Thesis, Dissertation, 2020
English
Publisher:2020
2020 55 see 2019 24 thesis
Diffusions on Wasserstein Spaces
Author:Lorenzo Dello Schiavo
Thesis, Dissertation, 2020
English
Publisher:Universitäts- und Landesbibliothek Bonn, Bonn, 2020
2020 56 thesis
Lp-Wasserstein and flux-limited gradient flows: Entropic discretization, convergence analysis and numerics
Author:Benjamin Söllner
Thesis, Dissertation, 2020
English
Publisher:2020
<–– 145 until 2020
+ 56 titles in 2020
= 201 titles till 2020
end 2020 e20
start 2021 s21
2021 1
Open Access
Wasserstein Autoencoders with Mixture of Gaussian Priors for Stylized Text Generation
by Ghabussi, Amirpasha Waterloo master
Probabilistic text generation is an important application of Natural Language Processing (NLP). Variational autoencoders and Wasserstein autoencoders are two...
Dissertation/ThesisCitation Online Jan 21,2021
Master's Thesis Presentation • Machine Learning ... Jan 21, 2021
2021 2 modified
A Generative Adversarial Network in Domain Adaptation by Utilizing the Wasserstein distance
by HSU,WEI-CHE;
許維哲
碩士 國立中正大學 電機工程研究所 107 Transfer learning is an important branch of machine learning, mainly used with unsupervised learning or semi-unsupervised learning, these...
Dissertation/ThesisCitation Online
2021 3
mputer Science Master's Thesis Presentation -- 21-1-2021
www.math.uwaterloo.ca › notice_prgms › wreg › list_full
Jan 21, 2021 — Thursday, 21 January 2021 at 10:00AM. Online presentation. Wasserstein Autoencoders with Mixture of Gaussian Priors for Stylized Text ...
by Amirpasha Ghabussi, AI Lab
2021 4
Projection in the 2-Wasserstein sense on structured measure ...
www.researchgate.net › publication › 343007004_Project...
Jul 19, 2020 — This thesis focuses on the approximation for the 2-Wasserstein metric of ... compute the 2-Wasserstein distance between a given measure and the structured measure. ... January 2021 · Bangladesh Journal of Medical Science.
Spring 2021: Optimal Transport - Master Optimisation - Université Paris-Saclay ... Regularization and Applications on Faster Wasserstein Distance Estimation with the Sinkhorn Divergence. ... PhD thesis, PSL Research University, 2017. [pdf].
2021 5
Wasserstein Autoencoders with Mixture of Gaussian Priors for Stylized Text Generation
by Ghabussi, Amirpasha
Probabilistic text generation is an important application of Natural Language Processing (NLP). Variational autoencoders and Wasserstein autoencoders are two...
Dissertation/ThesisCitation Online
2021 6 PDF
Extreme quantile regression: a coupling approach and ...
http://doukhan.u-cergy.fr › seminary › Bobbia
Jan 27, 2021 — Extreme quantile regression: a coupling approach and. Wasserstein distance. Benjamin Bobbia. Joint work with C.Dombry and D.Varron.
online OPEN ACCESS
Extreme quantile regression : a coupling approach and Wasserstein distance
by Bobbia, Benjamin
Université Bourgogne Franche-Comté, 2020
This work is related with the estimation of conditional extreme quantiles. More precisely, we estimate high quantiles of a real distribution conditionally to...
Dissertation/ThesisFull Text Online
2021 7
Projection in the 2-Wasserstein sense on structured measure ...
https://www.researchgate.net › publication › 343007004_...
Jun 3, 2021 — This thesis focuses on the approximation for the 2-Wasserstein metric of probability measures by structured measures. The set of structured ...
2021.8
Jan 21, 2021 — We present a semi-supervised approach using Wasserstein autoencoders and a mixture of Gaussian priors for topic-aware sentence generation. Our ...
You've visited this page 5 times. Last visit: 7/23/21
Decentralized Algorithms for Wasserstein Barycenters - arXiv
by D Dvinskikh · 2021 — Abstract: In this thesis, we consider the Wasserstein barycenter problem of discrete ... [v1] Tue, 4 May 2021 15:58:03 UTC (7,752 KB).
2021.10 PDF
ooth p-Wasserstein Distance: Structure, Empirical ...
http://proceedings.mlr.press › ...
by S Nietert · 2021 · Cited by 2 — The Wasserstein distance Wp is a discrepancy measure be- ... Learning, PMLR 139, 2021. Copyright 2021 by the author(s) ... PhD thesis, Paris-Sud University,.
2021.11
Pooling by Sliced-Wasserstein Embedding - NeurIPS 2021
https://neurips.cc › 2021 › ScheduleMultitrack
We evaluate our proposed pooling method on a wide variety of set-structured data, including point-cloud, graph, and image classification tasks, and demonstrate ...
Missing: (allintitle: | Must include: (allintitle:
2021.12 Ph.D. thesis
Wasserstein distance estimates for the distributions of ...
https://www.jmlr.org › papers › volume22
by JM Sanz-Serna · 2021 — (2021). One of the aims of all that literature is to study ... For the integrator EE, we prove that, in 2-Wasserstein distance and for a ... PhD thesis,.
2021.13
On the Wasserstein distance between classical sequences ...
by L Brown · 2020 · Cited by 7 — This paper was part of the first author's Ph.D. thesis. ... Licensed to Google Inc. Prepared on Thu Sep 9 03:55:28 EDT 2021 for download ...
2021.14
Wasserstein generative adversarial active learning for ...
https://open.metu.edu.tr › handle
by HA Duran · 2021 — Wasserstein generative adversarial active learning for anomaly detection with gradient ... 2021-9. Author. Duran, Hasan Ali. Metadata. Show full item record.
Wasserstein Autoregressive Models for Density Time Series
https://www.stat.colostate.edu › zhangKP2021
by C ZHANG · 2021 · Cited by 8 — Received 10 November 2020; Accepted 09 April 2021. Keywords: Random densities; Wasserstein metric; time series; distributional forecasting.
2021.16
Data Imputation using Wasserstein GAIN - JKU ePUB
https://epub.jku.at › obvulihs › content › titleinfo
by C Halmich · 2020 — The goal of this thesis was to proof that it is possible to use the GAIN algorithm together with the Wasserstein setting and apply it to impute missing values.
2021.17
Reproducing-Kernel Hilbert space regression with notes on the Wasserstein Distance
https://eprints.lancs.ac.uk › eprint
2021.18 PDF
On Linear Optimization over Wasserstein Balls - Man-Chung ...
https://manchungyue.com › wasserstein
by MC Yue · 2021 · Cited by 6 — June 7, 2021. Abstract. Wasserstein balls, which contain all probability measures within a pre-specified ... Master's thesis, Sapienza.
2021.19
Wasserstein GAN 1031 thesis [Chung il kim] - SlideShare
https://www.slideshare.net › ChungIllKim › wasserstein-...
Thesis of Wasserstein GAN. paper : https://arxiv.org/pdf/1701.07875v2.pdf.
You've visited this page 2 times. Last visit: 4/21/
2021.20
Permutation invariant networks to learn Wasserstein metrics
Wasserstein distance is one of the fundamental questions in mathematical analysis. The Wasserstein metric has received
2021.21
ttps://www.worldscientific.com › doi › abs
The Wasserstein geometry of nonlinear σ models and the ...
by M Carfora · 2017 · Cited by 15 — Nonlinear sigma models are quantum field theories describing, in the large deviation sense, random fluctuations of harmonic maps between a Riemann surface ...
2021.22
Wasserstein Adversarial Transformer for Cloud Workload Prediction
Arbat, Shivani Gajanan. University of Georgia, ProQuest Dissertations Publishing, 2021. 28643528.
Abstract/DetailsPreview - PDF (470 KB)
by J Cui · Thesis Apr1 5.pdf (1.148Mb) ... 04-16-2023 ... The results obtained in this paper include that Bures-Wasserstein simple projection mean ...
Master
2021 24
Master's Thesis Presentation • Machine Learning - Cheriton ...
https://cs.uwaterloo.ca › events › masters-thesis-presenta...
Jan 21, 2021 — We present a semi-supervised approach using Wasserstein autoencoders and a mixture of Gaussian priors for topic-aware sentence generation. Our ...
2021 25
DISSERTATION
Decentralized Algorithms for Wasserstein Barycenters
Dvinskikh, Darina ; 2021
Decentralized Algorithms for Wasserstein Barycenters
Online Access Available
2021 26 DISSERTATION
Inside and around Wasserstein barycenters
Kroshnin, Aleksei2021
OPEN ACCESS
Inside and around Wasserstein barycenters
No Online Access
2021 27 DISSERTATION
基于条件Wasserstein生成对抗网络的跨模态光伏出力数据生成方法
康明与2021
[Chinese Cross-modal photovoltaic output data generation method based on conditional Wasserstein generative adversarial network
Cuming and 2021]
2021 28 to thesis
DISSERTATION
Diffusion-Wasserstein Distances for Attributed Graphs
Barbe, Dominique2021
OPEN ACCESS
Diffusion-Wasserstein Distances for Attributed Graphs
No Online Access
2021 29 DISSERTATION
Finite volume approximation of optimal transport and Wasserstein gradient flows
Todeschi, Gabriele2021
OPEN ACCESS
Finite volume approximation of optimal transport and Wasserstein gradient flows
No Online Access
2021 30 DISSERTATION
A travers et autour des barycentres de Wasserstein
Kroshnin, Aleksei2021
OPEN ACCESS
A travers et autour des barycentres de Wasserstein
No Online Access
2021 31 DISSERTATION
Sliced-Wasserstein distance for large-scale machine learning : theory, methodology and extensions
Nadjahi, Kimia2021
OPEN ACCESS
Sliced-Wasserstein distance for large-scale machine learning : theory, methodology and extensions
No Online Access
2021 32 DISSERTATION
LI, Jiajin2021
Efficient and Provable Algorithms for Wasserstein Distributionally Robust Optimization in Machine Learning
No Online Access
2021 33
Wasserstein Autoencoders with Mixture of Gaussian Priors for ...
https://cs.uwaterloo.ca › events › masters-thesis-presenta...
https://cs.uwaterloo.ca › events › masters-thesis-presenta...
Jan 21, 2021 — Master's Thesis Presentation • Machine Learning — Wasserstein Autoencoders with Mixture of Gaussian Priors for Stylized Text Generation ...
2021 34 thesis
Flexibility properties and homology of Gromov-Vaserstein fibres
G De Vito, F Kutzschebauch - scholar.archive.org
The aim of this thesis consists in the study of a very concrete class of affine algebraic varieties,
ie the fibres of the so-called Gromov-Vaserstein fibration, which are of importance in the …
Related articles All 3 versions
Flexibility properties and homology of Gromov-Vaserstein fibres
Inaugural dissertation of the Faculty of Science, University of Bern
presented by Giorgio De Vito from Italy
2021 35
Wasserstein adversarial transformer for cloud workload predictionAuthors:Shivani Gajanan Arbat (Author), In Kee Kim (Degree supervisor), University of Georgia (Degree granting institution)
Summary:Resource provisioning is essential to optimize cloud operating costs and the performance of cloud applications. Understanding job arrival rates is critical for predicting future workloads to determine the proper amount of resources for provisioning. However, due to the dynamic patterns of cloud workloads, developing a model to accurately forecast job arrival rates is a challenging task. Previously, various prediction models, including Long-Short-Term-Memory (LSTM), have been employed to address the cloud workload prediction problem. Unfortunately, the current state-of-the-art LSTM model leverages recurrences to make a prediction, resulting in increased complexity and degraded computational efficiency as input sequences grow longer. To achieve both higher prediction accuracy and better computational efficiency, this work presents a novel time-series forecasting model for cloud resource provisioning, called WGAN-gp (Wasserstein Generative Adversarial Network with gradient penalty) Transformer. WGAN-gp Transformer is inspired by Transformer network and improved WGAN (Wasserstein Generative Adversarial Networks). Our proposed method adopts a Transformer network as the generator and a multi-layer perceptron network as a critic to improve the overall forecasting performance. WGAN-gp also employs MADGRAD (Momentumized, Adaptive, Dual Averaged Gradient Method for Stochastic Optimization) as the model's optimizer due its ability to converge faster and generalize better. Extensive experiments on the various real-world cloud workload datasets show improved performance and efficiency of our method. In particular, WGAN-gp Transformer shows 5x faster inference time with up to 5.1% higher prediction accuracy than the state-of-the-art workload prediction technique. Such faster inference time and higher prediction accuracy can be effectively used by cloud resource provisioning and autoscaling mechanisms. We then apply our model to cloud autoscaling and evaluate it on Google Cloud Platform with Facebook and Google cluster traces. We discuss the evaluation results showcasing that WGAN-gp Transformer-based autoscaling mechanism outperforms autoscaling with LSTM by reducing virtual machine over-provisioningShow more
Thesis, Dissertation, 2021
English
Publication:Masters Abstracts International
Publisher:ProQuest Dissertations & Theses, Ann Arbor, 2021
2021 36
使用WGAN-GP對臉部馬賽克進行眼睛補圖 = Eye In-painting Using WGAN-GP for Face Images with Mosaic / Shi yongWGAN-GP dui lian bu ma sai ke jin xing yan jing bu tu = Eye In-painting Using WGAN-GP for Face Images with MosaicShow more
Authors:吳承軒, 著, H. T. Chang, Cheng Hsuan Wu, 張賢宗 / Chengxuan Wu, Xianzong Zhang
Thesis, Dissertation, 2019[min 108]
Chinese, Chu ban
Publisher:長庚大學, Tao yuan shi, 2019[min 108]
2021 37 thesis
Automatic Generation of Floorplans using Generative Adversarial NetworksAuthors:Sneha Suhitha Galiveeti (Author), Chitaranjan Das (Thesis advisor)
Summary:In the present day, demand for construction of houses is increasing rapidly. But creating and designing a floorplan requires a lot of creativity, technical knowledge and mathematical skills. The number of architects with these skills are not adequate to meet the requirements of the rapidly growing demand. We can use Machine Learning to solve this problem of floorplan generation. This project explores the idea of generation of multiple floorplans using deep learning models especially Generative Adversarial Networks(GANs). This work concentrates on the generation of rasterized of floorplans. The main approach is to let GAN treat floorplans as raster images and learn their distribution to produce new floorplans. This work explored multiple models of GANs like simple DCGAN, LSGAN, WGAN, StyleGAN etc. and studied the pros and cons of each model over two major datasets Structure3D and Graph2Plan. This work also explored the conditional generation of floorplans i.e., controlling the layout of generated floorplans by giving input condition to the models in terms of types of rooms presentShow more
Thesis, Dissertation, 2021
English
Publisher:Pennsylvania State University, [University Park, Pennsylvania], 2021
<–– 201 titles before 2021
+ 37 in 2021
= 238 till 2021
end 2021 e21
start 2022 s22
2022.1 [PDF] archives-ouvertes.fr
Lagrangian discretization of variationnal problems in Wasserstein spaces
C Sarrazin - 2022 - tel.archives-ouvertes.fr
… This is a very nice feature of this euclidean setting, and one of the reasons why we will
use quadratic Wasserstein distances through most of this thesis. On the other hand, for the …
2022.2
Computational Inversion with Wasserstein Distances and ...
https://academiccommons.columbia.edu › dhnq-j497
https://academiccommons.columbia.edu › dhnq-j497
by W Ding · 2022 — This thesis presents a systematic computational investigation of loss functions in solving inverse problems of partial differential equations.
2022.3
Non-parametric threshold for smoothed empirical Wasserstein ...
https://dspace.mit.edu › bitstream › handle › Jia-zyji...PDF
by Z Jia · 2022 — c○ Massachusetts Institute of Technology 2022. ... proper way, which benefits my not only in the write-up of this thesis, and also among.
2022.4 MIT B.S. thesis
Non-parametric threshold for smoothed empirical Wasserstein distance
https://dspace.mit.edu › bitstream › handle › Jia-zyji...
https://dspace.mit.edu › bitstream › handle › Jia-zyji...PDF
by Z Jia · 2022 — c○ Massachusetts Institute of Technology 2022. ... proper way, which benefits my not only in the write-up of this thesis, and also among.
2022.5 [PDF] escholarship.org
A Karimi - 2022 - escholarship.org
The Perron–Frobenius and Koopman operators provide natural dual settings to investigate
the dynamics of complex systems. In this thesis we focus on certain pertinent concepts and …
2022.6 see 2021 thesis
MR4451910 Prelim Jekel, David; Li, Wuchen; Shlyakhtenko, Dimitri;
Tracial smooth functions of non-commuting variables and the free Wasserstein manifold. Dissertationes Math. 580 (2022), 1–150. 46L54 (35Q49 46L52 58D99 94A17)
Review PDF Clipboard Journal Article
2022 7 DISSERTATION
Lagrangian discretization of variational problems in Wasserstein spaces
Sarrazin, Clément2022
OPEN ACCESS
Lagrangan discretization of variational problems in Wasserstein spaces
No Online Access
2022 8
DISSERTATION
Computational Inversion with Wasserstein Distances and Neural Network Induced Loss Functions
Ding, Wen ; 2022
Computational Inversion with Wasserstein Distances and Neural Network Induced Loss Functions
Online Access Available
2022 9 DISSERTATION
On Adversarial Regularization of Tabular Wasserstein Generative Adversarial Networks
Eiring, Sverre Roalsø2022
OPEN ACCESS
On Adversarial Regularization of Tabular Wasserstein Generative Adversarial Networks
No Online Access
3022 10
DeepWSD: Projecting Degradations in Perceptual Space to
Wasserstein Distance in Deep Feature Spacehttps://arxiv.org › eess
https://arxiv.org › eess
by X Liao · 2022 — The deep Wasserstein distance (DeepWSD) performed on features from neural networks enjoys ... Comments: ACM Multimedia 2022 accepted thesis.
deep Wasserstein distance (DeepWSD) p
2022 11 DISSERTATION
Parallel translations, Newton flows and Q-Wiener processes on the Wasserstein space
Ding, Hao2022
OPEN ACCESS
Parallel translations, Newton flows and Q-Wiener processes on the Wasserstein space
No Online Access
Parallel translations, Newton flows and Q-Wiener processes on the Wasserstein space
2022 12 DISSERTATION
황진미2022
Wasserstein 행렬 평균과 작용소로의 확장
No Online Access
2022 13
Computational Inversion with Wasserstein Distances and Neural Network Induced Loss Functions. Thesis (Ph.D.)–Columbia University. 2022. 185 pp. ISBN: 979-8845-75608-4, ProQuest LLC
Review PDF Clipboard Series Thesis
022 14
Computational Inversion with Wasserstein Distances and Neural Network Induced Loss FunctionsAuthor:Wen Ding
Summary:This thesis presents a systematic computational investigation of loss functions in solving inverse problems of partial differential equations. The primary efforts are spent on understanding optimization-based computational inversion with loss functions defined with the Wasserstein metrics and with deep learning models. The scientific contributions of the thesis can be summarized in two directions. In the first part of this thesis, we investigate the general impacts of different Wasserstein metrics and the properties of the approximate solutions to inverse problems obtained by minimizing loss functions based on such metrics. We contrast the results to those of classical computational inversion with loss functions based on the ?² and ?⁻ metric. We identify critical parameters, both in the metrics and the inverse problems to be solved, that control the performance of the reconstruction algorithms. We highlight the frequency disparity in the reconstructions with the Wasserstein metrics as well as its consequences, for instance, the pre-conditioning effect, the robustness against high-frequency noise, and the loss of resolution when data used contain random noiseShow more
Thesis, Dissertation, 2022
English
Publisher:[publisher not identified], [New York, N.Y.?], 2022
2022 15
Non-parametric threshold for smoothed empirical Wasserstein distanceAuthors:Zeyu Jia (Author), Yury Polyanskiy, Sasha Rakhlin, Massachusetts Institute of Technology
Abstract:Consider an empirical measure P[subscript n] induced by n iid samples from a d-dimensional K-subgaussian distribution P. We show that when K < [sigma], the Wasserstein distance [mathematical formula] converges at the parametric rate 0(1/n), and when K > [sigma], there exists a K-subgaussian distribution P such that [mathemetical formula]. This resolves the open problems in[7], closes the gap between where we get parametric rate and where we do not have parametric rate. Our result provides a complete characterization of the range of parametric rates for subgaussian PShow more
Thesis, Dissertation, 2022
English
Publisher:Massachusetts Institute of Technology, Cambridge, Massachusetts, 2022
2022 16
Perfomance comparison of CGANs and WGANs for crop disease image synthesisAuthors:Arsene Djatche, Achim Ibenthal, Cordula Reisch, Hochschule für Angewandte Wissenschaft und Kunst (Other)
Thesis, Dissertation, 2022
English
Publisher:2022
2022 17 see 2018 2 a thesis MJT
Learning and inference with Wasserstein metricsAuthors:Tomaso Poggio (Contributor), Massachusetts Institute of Technology Department of Brain and Cognitive Sciences (Contributor), Frogner, Charles (Charles Albert) (Creator)
Summary:Thesis: Ph. D., Massachusetts Institute of Technology, Department of Brain and Cognitive Sciences, 2018
Downloadable Archival Material, 2019-03-01T19:52:20Z
English
Publisher:Massachusetts Institute of Technology, 2019-03-01T19:52:20Z
Access Free
2022 18
MR4511551 Thesis Yenisey, Mehmet; The Metric Geometry
Nature of Wasserstein Spaces of Probability Measures: On the Point of View of Submetry Projections. Thesis (Ph.D.)–University of Kansas. 2022. 68 pp. ISBN: 979-8352-92325-2, ProQuest LLC
Review PDF Clipboard Series Thesis
2022 19
thesis_July26th.pdf - Toronto Math Blogs
http://blog.math.toronto.edu › files › 2022/08 › thes...
Optimal transport, congested transport, and Wasserstein generative ... The second part of this thesis presents new algorithms for generative.
2022 20
On the Wasserstein median of probability measures - arXivhttps://arxiv.org › pdf
https://arxiv.org › pdfPDF
by K You · 2022 — In the field of optimal transport, the Wasserstein barycenter ... ME] 9 Sep 2022 ... thesis, University of California Los Angeles.
2022 21 thesis
Generative Adversarial Networks and Data StarvationAuthors:Brendan Jugan (Author), Patrick Drew Mcdaniel, Schreyer Honors College
Summary:Generative adversarial networks (GAN) have shown impressive results in data generation tasks, particularly in the image domain [1, 2, 3, 4]. Recent research has employed GANs to generate high-quality synthetic images of animals, scenes in nature, and even complex human faces. While GANs have seen great success, they are notoriously difficult to train. If improperly configured, their adversarial nature can lead to failures such as model divergence and mode collapse. It has been documented that training dataset size and quality influences GAN sensitivity to these failure modes [5]. However, there is limited research as to the extent of data starvation's negative impact on modern architectures. In this paper, we present a framework for evaluating modern architecture performance when given limited training data. Specifically, we apply data starvation techniques to GAN training and evaluate their performances using common metrics utilized by the research community. To accomplish this, we use a state-of-the-art image generation benchmark dataset [6], as well as publicly available architecture implementations provided by the Pohang University of Science and Technology's Computer Vision Lab [7]. We evaluate our data-starved GANs by recording inception score and Frechet inception distance, which are effective, and commonly used metrics for measuring GAN performance [8]. Our results show that SNGAN and BigGAN require more data than DCGAN, WGAN-GP, and SAGAN to avoid model divergence. We also find that data starvation has fewer performance implications when used on datasets from less complex domains, like those including handwritten digitsShow more
Thesis, Dissertation, 2022
English
Publisher:Pennsylvania State University, [University Park, Pennsylvania], 2022
2022 22
Gromov-Wasserstein Distances and their Lower BoundsAuthors:Christoph Alexander Weitkamp, Prof Munk, Dr Proksch
Summary:In various applications in biochemistry, computer vision and machine learning, it is of great interest to compare general objects in a pose invariant manner. Recently, the following approach has received increased attention: Model the objects considered as metric measure spaces and compare them with the Gromov-Wasserstein distance. While this distance has many theoretically appealing properties and is a natural distance concept in numerous frameworks, it is NP-hard to compute. In consequence, several alternatives to the precise determination of this distance have been proposed. On the one h..Show more
Thesis, Dissertation, 2022
English
Publisher:2022
2022 23
MR4533107 Thesis Milne, Tristan;
Optimal Transport, Congested Transport, and Wasserstein Generative Adversarial Networks. Thesis (Ph.D.)–University of Toronto (Canada). 2022. 199 pp. ISBN: 979-8357-55114-6, ProQuest LLC
Review PDF Clipboard Series Thesis
<–– 238 titles before 2022
+ 23 titles in 2022
= 251 dissertations till 2022
2023 1
Integration of heterogeneous single cell data with Wasserstein Generative Adversarial Networks
Authors:Giansanti, V (Contributor), ANTONIOTTI, MARCO (Contributor), SCHETTINI, RAIMONDO (Contributor), GIANSANTI, VALENTINA (Creator)
Show more
Summary:Tessuti, organi e organismi sono sistemi biologici complessi, oggetto di studi che mirano alla caratterizzazione dei loro processi biologici. Comprendere il loro funzionamento e la loro interazione in campioni sani e malati consente di interferire, correggere e prevenire le disfunzioni dalle quali si sviluppano possibilmente le malattie. I recenti sviluppi nelle tecnologie di sequenziamento single-cell stanno ampliano la capacità di profilare, a livello di singola cellula, diversi layer molecolari (trascrittoma, genoma, epigenoma, proteoma). Il numero, la grandezza e le diverse modalità dei dataset prodotti è in continua crescita. Ciò spinge allo sviluppo di robusti metodi per l’integrazione di dataset multiomici, che siano essi descrittivi o meno delle stesse cellule. L’integrazione di più fonti di informazione produce una descrizione più ampia e completa dell’intero sistema analizzato. La maggior parte dei sistemi di integrazione disponibili ad oggi consente l’analisi simultanea di un numero limitato di omiche (generalmente due) e richiede conoscenze pregresse riguardo le loro relazioni. Questi metodi spesso impongono la traduzione di una modalità nelle variabili espresse da un altro dato (ad esempio, i picchi di ATAC vengono convertiti in gene activity matrix). Questo step introduce un livello di approssimazione nel dato che potrebbe pregiudicare le analisi svolte in seguito. Da qui nasce MOWGAN (Multi Omic Wasserstein Generative Adversarial Network), un framework basato sul deep-learning, per la simulazione di dati multimodali appaiati in grado di supportare un alto numero di dataset (più di due) e agnostico sulle relazioni che intercorrono tra loro (non viene imposta alcuna assunzione). Ogni modalità viene proiettata in uno spazio descrittivo ridotto, le cui dimensioni sono fissate per tutti i datasets. Questo processo previene la traduzione tra modalità. Le cellule, descritte da vettori nello spazio ridotto, vengono ordinate in base alla prima componente della
Show mor
Thesis, Dissertation, 2023-02-17T00:00:00+01:00
English
Publisher:Università degli Studi di Milano-Bicocca country:Italy, 2023-02-17T00:00:00+01:00
Applications of the Bures-Wasserstein Distance in Linear ...
share.com › articles › thesis › Applications_o...
Figshare
https://figshare.com › articles › thesis › Applications_o...
2023 3. thesis master see 2021
Efficient and Robust Classification for Positive Definite Matrices with Wasserstein Metric
The results obtained in this paper include that Bures-Wasserstein simple ... dc.type, Master's Thesis, en_US ... dc.embargo.enddate, 2023-04-16, en_US.
2023 4. thesis see 2019
Optimal Control in Wasserstein Spaces
https://www.researchgate.net › publication › 337311998...
ResearchGate
https://www.researchgate.net › publication › 337311998...
Jan 4, 2023 — In this thesis, we extend for the first time several of these concepts to the framework of control theory.The first result p
20235
Semidefinite Programming Relaxations of the Simplified Wasserstein...
by Cheng, Jiahui
2023
The Simplified Wasserstein Barycenter problem, the problem of picking k points each chosen from a distinct set of n points as to minimize the sum of distances...
Dissertation/ThesisCitation Online
Open Access
<–– 251 titles before 2023
+ 5 title in 2023
= 256 dissertations total
end 2023
——————————————————————————
—————————————————yyy
WurldCat
2008 comp pr
Hamilton-Jacobi Equations in the Wasserstein SpaceAuthors:Gangbo, Wilfrid (Creator), Nguyen, Truyen (Creator), Tudorascu, Adrian (Creator)
Summary:We introduce a concept of viscosity solutions for Hamilton-Jacobi equations (HJE) in the Wasserstein space. We prove existence of solutions for the Cauchy problem for certain Hamiltonians defined on the Wasserstein space over the real line. In order to illustrate the link between HJE in the Wasserstein space and Fluid Mechanics, in the last part of the paper we focus on a special Hamiltonian. The characteristics for these HJE are solutions of physical systems in finite dimensional spacesShow more
Computer Program, 2008-06
English
Publisher:International Press of Boston, 2008-06
Access Free
2016 comp pr
Subgeometric rates of convergence in Wasserstein distance for Markov chainsAuthors:Durmus, Alain (Creator), Fort, Gersende (Creator), Moulines, Éric (Creator)
Summary:In this paper, we provide sufficient conditions for the existence of the invariant distribution and for subgeometric rates of convergence in Wasserstein distance for general state-space Markov chains which are (possibly) not irreducible. Compared to (Ann. Appl. Probab. 24 (2) (2014) 526–552), our approach is based on a purely probabilistic coupling construction which allows to retrieve rates of convergence matching those previously reported for convergence in total variation in (Bernoulli 13 (3) (2007) 831–848). ¶ Our results are applied to establish the subgeometric ergodicity in Wasserstein distance of non-linear autoregressive models and of the pre-conditioned Crank–Nicolson Markov chain Monte Carlo algorithm in Hilbert spaceShow more
Computer Program, 2016-11
English
Publisher:Institut Henri Poincaré, 2016-11
Access Free
2014 comp pr
On the mean speed of convergence of empirical and occupation measures in Wasserstein distanceAuthors:Boissard, Emmanuel (Creator), Le Gouic, Thibaut (Creator)
Summary:In this work, we provide non-asymptotic bounds for the average speed of convergence of the empirical measure in the law of large numbers, in Wasserstein distance. We also consider occupation measures of ergodic Markov chains. One motivation is the approximation of a probability measure by finitely supported measures (the quantization problem). It is found that rates for empirical or occupation measures match or are close to previously known optimal quantization rates in several cases. This is notably highlighted in the example of infinite-dimensional Gaussian measuresShow more
Computer Program, 2014-05
English
Publisher:Institut Henri Poincaré, 2014-05
Access Free
2008 comp pr
Spectral gaps in Wasserstein distances and the 2D stochastic Navier–Stokes equationsAuthors:Hairer, Martin (Creator), Mattingly, Jonathan C. (Creator)
Summary:We develop a general method to prove the existence of spectral gaps for Markov semigroups on Banach spaces. Unlike most previous work, the type of norm we consider for this analysis is neither a weighted supremum norm nor an $\L^{p}$ -type norm, but involves the derivative of the observable as well and hence can be seen as a type of 1-Wasserstein distance. This turns out to be a suitable approach for infinite-dimensional spaces where the usual Harris or Doeblin conditions, which are geared toward total variation convergence, often fail to hold. In the first part of this paper, we consider semigroups that have uniform behavior which one can view as the analog of Doeblin’s condition. We then proceed to study situations where the behavior is not so uniform, but the system has a suitable Lyapunov structure, leading to a type of Harris condition. We finally show that the latter condition is satisfied by the two-dimensional stochastic Navier–Stokes equations, even in situations where the forcing is extremely degenerate. Using the convergence result, we show that the stochastic Navier–Stokes equations’ invariant measures depend continuously on the viscosity and the structure of the forcingShow more
Computer Program, 2008-11
English
Publisher:The Institute of Mathematical Statistics, 2008-11
2009 comp pr
Stein’s method and Poisson process approximation for a class of Wasserstein metricsAuthor:Schuhmacher, Dominic (Creator)
Summary:Based on Stein’s method, we derive upper bounds for Poisson process approximation in the L1-Wasserstein metric d2(p), which is based on a slightly adapted Lp-Wasserstein metric between point measures. For the case p=1, this construction yields the metric d2 introduced in [Barbour and Brown Stochastic Process. Appl. 43 (1992) 9–31], for which Poisson process approximation is well studied in the literature. We demonstrate the usefulness of the extension to general p by showing that d2(p)-bounds control differences between expectations of certain pth order average statistics of point processes. To illustrate the bounds obtained for Poisson process approximation, we consider the structure of 2-runs and the hard core model as concrete examplesShow more
Computer Program, 2009-05
English
Publisher:Bernoulli Society for Mathematical Statistics and Probability, 2009-05
Access Free
2017 eBook
Topological Optimization and Optimal Transport : In the Applied SciencesAuthors:Maïtine Bergounioux, Guillaume Carlier, Thierry Champion, Édouard Oudet, Martin Rumpf, Filippo Santambrogio
Summary:By discussing topics such as shape representations, relaxation theory and optimal transport, trends and synergies of mathematical tools required for optimization of geometry and topology of shapes are explored. Furthermore, applications in science and engineering, including economics, social sciences, biology, physics and image processing are covered. ContentsPart I Geometric issues in PDE problems related to the infinity Laplace operator Solution of free boundary problems in the presence of geometric uncertainties Distributed and boundary control problems for the semidiscrete Cahn-Hilliard/Navier-Stokes system with nonsmooth Ginzburg-Landau energies High-order topological expansions for Helmholtz problems in 2D On a new phase field model for the approximation of interfacial energies of multiphase systems Optimization of eigenvalues and eigenmodes by using the adjoint method Discrete varifolds and surface approximation Part II Weak Monge-Ampere solutions of the semi-discrete optimal transportation problem Optimal transportation theory with repulsive costs Wardrop equilibria: long-term variant, degenerate anisotropic PDEs and numerical approximations On the Lagrangian branched transport model and the equivalence with its Eulerian formulation On some nonlinear evolution systems which are perturbations of Wasserstein gradient flows Pressureless Euler equations with maximal density constraint: a time-splitting scheme Convergence of a fully discrete variational scheme for a thin-film equatio Interpretation of finite volume discretization schemes for the Fokker-Planck equation as gradient flows for the discrete Wasserstein distanceShow more
eBook, 2017
English
Publisher:De Gruyter, Berlin, 2017
Also available asPrint Book
View AllFormats & Editions
2010 comp pr
The heat equation on manifolds as a gradient flow in the Wasserstein spaceAuthor:Erbar, Matthias (Creator)
Summary:We study the gradient flow for the relative entropy functional on probability measures over a Riemannian manifold. To this aim we present a notion of a Riemannian structure on the Wasserstein space. If the Ricci curvature is bounded below we establish existence and contractivity of the gradient flow using a discrete approximation scheme. Furthermore we show that its trajectories coincide with solutions to the heat equationShow more
Computer Program, 2010-02
English
Publisher:Institut Henri Poincaré, 2010-02
Access Free
2011 comp f9le
Deconvolution for the Wasserstein metric and geometric inferenceAuthors:Caillerie, Claire (Creator), Chazal, Frédéric (Creator), Dedecker, Jérôme (Creator), Michel, Bertrand (Creator)
Summary:Recently, Chazal, Cohen-Steiner and Mérigot have defined a distance function to measures to answer geometric inference problems in a probabilistic setting. According to their result, the topological properties of a shape can be recovered by using the distance to a known measure ν, if ν is close enough to a measure μ concentrated on this shape. Here, close enough means that the Wasserstein distance W2 between μ and ν is sufficiently small. Given a point cloud, a natural candidate for ν is the empirical measure μn. Nevertheless, in many situations the data points are not located on the geometric shape but in the neighborhood of it, and μn can be too far from μ. In a deconvolution framework, we consider a slight modification of the classical kernel deconvolution estimator, and we give a consistency result and rates of convergence for this estimator. Some simulated experiments illustrate the deconvolution method and its application to geometric inference on various shapes and with various noise distributionsShow more
Computer File, 2011
English
Publisher:The Institute of Mathematical Statistics and the Bernoulli Society, 2011
2010 comp file
Quantitative bounds for Markov chain convergence: Wasserstein and total variation distancesAuthors:Madras, Neal (Creator), Sezer, Deniz (Creator)
Summary:We present a framework for obtaining explicit bounds on the rate of convergence to equilibrium of a Markov chain on a general state space, with respect to both total variation and Wasserstein distances. For Wasserstein bounds, our main tool is Steinsaltz’s convergence theorem for locally contractive random dynamical systems. We describe practical methods for finding Steinsaltz’s “drift functions” that prove local contractivity. We then use the idea of “one-shot coupling” to derive criteria that give bounds for total variation distances in terms of Wasserstein distances. Our methods are applied to two examples: a two-component Gibbs sampler for the Normal distribution and a random logistic dynamical systemShow more
Computer File, 2010-08
English
Publisher:Bernoulli Society for Mathematical Statistics and Probability, 2010-08
2014 comp pr
Subgeometric rates of convergence of Markov processes in the Wasserstein metricAuthor:Butkovsky, Oleg (Creator)
Summary:We establish subgeometric bounds on convergence rate of general Markov processes in the Wasserstein metric. In the discrete time setting we prove that the Lyapunov drift condition and the existence of a “good” $d$-small set imply subgeometric convergence to the invariant measure. In the continuous time setting we obtain the same convergence rate provided that there exists a “good” $d$-small set and the Douc–Fort–Guillin supermartingale condition holds. As an application of our results, we prove that the Veretennikov–Khasminskii condition is sufficient for subexponential convergence of strong solutions of stochastic delay differential equationsShow more
Computer Program, 2014-04
English
Publisher:The Institute of Mathematical Statistics, 2014-04
2009 comp pr 2
Entropic measure and Wasserstein diffusionAuthors:von Renesse, Max-K. (Creator), Sturm, Karl-Theodor (Creator)
Summary:We construct a new random probability measure on the circle and on the unit interval which in both cases has a Gibbs structure with the relative entropy functional as Hamiltonian. It satisfies a quasi-invariance formula with respect to the action of smooth diffeomorphism of the sphere and the interval, respectively. The associated integration by parts formula is used to construct two classes of diffusion processes on probability measures (on the sphere or the unit interval) by Dirichlet form methods. The first one is closely related to Malliavin’s Brownian motion on the homeomorphism group. The second one is a probability valued stochastic perturbation of the heat flow, whose intrinsic metric is the quadratic Wasserstein distance. It may be regarded as the canonical diffusion process on the Wasserstein spaceShow more
Computer Program, 2009-05
English
Publisher:The Institute of Mathematical Statistics, 2009-05
Access Free
2011 comp pr
Wasserstein geometry of Gaussian measuresAuthor:Takatsu, Asuka (Creator)
Summary:This paper concerns the Riemannian/Alexandrov geometry of Gaussian measures, from the view point of the $L^{2}$-Wasserstein geometry. The space of Gaussian measures is of finite dimension, which allows to write down the explicit Riemannian metric which in turn induces the $L^{2}$-Wasserstein distance. Moreover, its completion as a metric space provides a complete picture of the singular behavior of the $L^{2}$-Wasserstein geometry. In particular, the singular set is stratified according to the dimension of the support of the Gaussian measures, providing an explicit nontrivial example of Alexandrov space with extremal setsShow more
Computer Program, 2011-12
English
Publisher:Osaka University and Osaka City University, Departments of Mathematics, 2011-12
Access Free
2016 article Peer-reviewed
Discrete Wasserstein barycenters: optimal transport for discrete dataAuthors:Ethan Anderes, Steffen Borgwardt, Jacob Miller
Summary:Wasserstein barycenters correspond to optimal solutions of transportation problems for several marginals, and as such have a wide range of applications ranging from economics to statistics and computer science. When the marginal probability measures are absolutely continuous (or vanish on small sets) the theory of Wasserstein barycenters is well-developed [see the seminal paper (Agueh and Carlier in SIAM J Math Anal 43(2):904-924, 2011)]. However, exact continuous computation of Wasserstein barycenters in this setting is tractable in only a small number of specialized cases. Moreover, in many applications data is given as a set of probability measures with finite support. In this paper, we develop theoretical results for Wasserstein barycenters in this discrete setting. Our results rely heavily on polyhedral theory which is possible due to the discrete structure of the marginals. The results closely mirror those in the continuous case with a few exceptions. In this discrete setting we establish that Wasserstein barycenters must also be discrete measures and there is always a barycenter which is provably sparse. Moreover, for each Wasserstein barycenter there exists a non-mass-splitting optimal transport to each of the discrete marginals. Such non-mass-splitting transports do not generally exist between two discrete measures unless special mass balance conditions hold. This makes Wasserstein barycenters in this discrete setting special in this regard. We illustrate the results of our discrete barycenter theory with a proof-of-concept computation for a hypothetical transportation problem with multiple marginals: distributing a fixed set of goods when the demand can take on different distributional shapes characterized by the discrete marginal distributions. A Wasserstein barycenter, in this case, represents an optimal distribution of inventory facilities which minimize the squared distance/transportation cost totaled over all demandsShow more
Article, 2016
Publication:Mathematical Methods of Operations Research, 84, 201610, 389
Publisher:2016
2010 eBook
Differential forms on Wasserstein space and infinite-dimensional Hamiltonian systemsAuthors:Wilfrid Gangbo, Hwa Kil Kim, Tommaso Pacini
eBook, 2010
English
Publisher:American Mathematical Society, Providence, R.I., 2010
Also available asPrint Book
View AllFormats & Editions
2018 Peer-reviewed
Lp-WGAN: Using Lp-norm normalization to stabilize Wasserstein generative adversarial networksAuthors:Changsheng Zhou, Jiangshe Zhang, Junmin Liu
Summary:Wasserstein generative adversarial networks (Wasserstein GANs, WGAN) improve the performance of GANs significantly by imposing the Lipschitz constraints on the critic, which is implemented by weight clipping. In this work, we argue that weight clipping could result in a side effect called area collapse by modifying orientations of weights heavily. To fix this issue, a novel method called Lp-WGAN is presented, where lp -norm normalization is employed to impose the constraints. This method restricts the searching space of weights within a low-dimensional manifold and focuses on searching orientations of weights. Experiments on toy datasets show that Lp-WGAN could spread probability mass and find the underlying distribution earlier than WGAN with weight clipping. Results on the LSUN bedroom dataset and CIFAR-10 dataset show that the proposed method could stabilize training better, generate competitive images earlier and get higher evaluation scoresShow more
Article, 2018
Publication:Knowledge-Based Systems, 161, 20181201, 415
Publisher:2018
————————bbb
———————————
Search links
Open Access Theses and Dissertations: OATD
oatd.org
Advanced research and scholarship. Theses and dissertations, free to find, free to use. Advanced search options.
Advanced Search - ProQuest Dissertations & Theses Global ...
GMath Geneology Project
MR
ProQuest Advanced Search
24 with wasserstein in title
ProQuest Advanced Search
Berkley library
___________________________________________________
end end end end end end end end end end end end
——————————————
Hamilton-Jacobi Equations in the Wasserstein Space
https://www.uakron.edu › math › research › hamilton-j...
https://www.uakron.edu › math › research › hamilton-j...
This project aims to study a class of dynamical systems on the Wasserstein space of probability measures corresponding to some fundamental systems of partial ...
2022t hesis?
Hierarchical sliced Wasserstein distance - Nhat Ho
https://nhatptnk8912.github.io › Hierarchical_SW
ongzheng Ren† Huy Nguyen† Litu Rout† Tan Nguyen⋄ Nhat Ho† University of Texas, PD
by K Nguyen · 2022 · Cited by 1 — September 28, 2022. Abstract. Sliced Wasserstein (SW) distance has been widely used in different application scenarios.
Abstract
Sliced Wasserstein (SW) distance has been widely used in different application scenarios
since it can be scaled to a large number of supports without suffering from the curse of
dimensionality. The value of sliced Wasserstein distance is the average of transportation cost
between one-dimensional representations (projections) of original measures that are obtained
by Radon Transform (RT). Despite its efficiency in the number of supports, estimating the
sliced Wasserstein requires a relatively large number of projections in high-dimensional settings.
Therefore, for applications where the number of supports is relatively small compared with the
dimension, e.g., several deep learning applications where the mini-batch approaches are utilized,
the complexities from matrix multiplication of Radon Transform become the main computational
bottleneck. To address this issue, we propose to derive projections by linearly and randomly
combining a smaller number of projections which are named bottleneck projections. We explain
the usage of these projections by introducing Hierarchical Radon Transform (HRT) which is
constructed by applying Radon Transform variants recursively. We then formulate the approach
into a new metric between measures, named Hierarchical Sliced Wasserstein (HSW) distance.
By proving the injectivity of HRT, we derive the metricity of HSW. Moreover, we investigate the
theoretical properties of HSW including its connection to SW variants and its computational and
sample complexities. Finally, we compare the computational cost and generative quality of HSW
with the conventional SW on the task of deep generative modeling using various benchmark
1
___________________________
Johannes Wiesel - Publications - Google Sites
https://sites.google.com › view › publications
A characterisation of convex order using the 2-Wasserstein distance, 2022. ... and risk management and its dynamics in time, DPhil Thesis, Oxford, 2020.
CV_06_2022.pdf - Damian Dąbrowski
https://www.damiandabrowski.eu › pdf › CV_06_..
Thesis: Characterization of Sobolev-Slobodeckij spaces using geometric ... Necessary condition for rectifiability involving Wasserstein distance W2.
3 pages
2020
Necessary Condition for Rectifiability Involving Wasserstein Distance W2
D Dąbrowski
International Mathematics Research Notices 2020 (22), 8936-8972
==========
|
|
|
|
|
|
|
