Afficher la notice abrégée

hal.structure.identifierInstitut de Mathématiques de Bordeaux [IMB]
dc.contributor.authorHOUDARD, Antoine
hal.structure.identifierInstitut de Mathématiques de Bordeaux [IMB]
dc.contributor.authorLECLAIRE, Arthur
hal.structure.identifierInstitut de Mathématiques de Bordeaux [IMB]
dc.contributor.authorPAPADAKIS, Nicolas
hal.structure.identifierEquipe Image - Laboratoire GREYC - UMR6072
dc.contributor.authorRABIN, Julien
dc.date.accessioned2024-04-04T02:47:21Z
dc.date.available2024-04-04T02:47:21Z
dc.identifier.urihttps://oskar-bordeaux.fr/handle/20.500.12278/191635
dc.description.abstractEnThe use of optimal transport cost for learning generative models has become popular with Wasserstein Generative Adversarial Networks (WGAN). Training of WGAN relies on a theoretical background: the calculation of the gradient of the optimal transport cost with respect to the generative model parameters. We first demonstrate that such gradient may not be defined, which can result in numerical instabilities during gradient-based optimization. We address this issue by stating a valid differentiation theorem in the case of entropic regularized transport and specify conditions under which existence is ensured. By exploiting the discrete nature of empirical data, we formulate the gradient in a semi-discrete setting and propose an algorithm for the optimization of the generative model parameters. Finally, we illustrate numerically the advantage of the proposed framework.
dc.description.sponsorshipGeneralized Optimal Transport Models for Image processing - ANR-16-CE33-0010
dc.language.isoen
dc.title.enOn the Existence of Optimal Transport Gradient for Learning Generative Models
dc.typeDocument de travail - Pré-publication
dc.identifier.doi10.48550/arXiv.2102.05542
dc.subject.halInformatique [cs]/Apprentissage [cs.LG]
dc.subject.halMathématiques [math]/Statistiques [math.ST]
dc.identifier.arxiv2102.05542v1
bordeaux.hal.laboratoriesInstitut de Mathématiques de Bordeaux (IMB) - UMR 5251*
bordeaux.institutionUniversité de Bordeaux
bordeaux.institutionBordeaux INP
bordeaux.institutionCNRS
hal.identifierhal-03137342
hal.version1
hal.origin.linkhttps://hal.archives-ouvertes.fr//hal-03137342v1
bordeaux.COinSctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.au=HOUDARD,%20Antoine&LECLAIRE,%20Arthur&PAPADAKIS,%20Nicolas&RABIN,%20Julien&rft.genre=preprint


Fichier(s) constituant ce document

FichiersTailleFormatVue

Il n'y a pas de fichiers associés à ce document.

Ce document figure dans la(les) collection(s) suivante(s)

Afficher la notice abrégée