Afficher la notice abrégée

Overrelaxed Sinkhorn-Knopp Algorithm for Regularized Optimal Transport

dc.contributor.authorTHIBAULT, Alexis
hal.structure.identifierCEntre de REcherches en MAthématiques de la DEcision [CEREMADE]
dc.contributor.authorCHIZAT, Lenaic
hal.structure.identifierInstitut National des Sciences Appliquées - Toulouse [INSA Toulouse]
hal.structure.identifierInstitut de Mathématiques de Toulouse UMR5219 [IMT]
dc.contributor.authorDOSSAL, Charles
hal.structure.identifierInstitut de Mathématiques de Bordeaux [IMB]
dc.contributor.authorPAPADAKIS, Nicolas
dc.date.accessioned2024-04-04T03:00:18Z
dc.date.available2024-04-04T03:00:18Z
dc.date.conference2017-12-09
dc.identifier.urihttps://oskar-bordeaux.fr/handle/20.500.12278/192806
dc.description.abstractEnThis article describes a method for quickly computing the solution to the regularized optimal transport problem. It generalizes and improves upon the widely-used iterative Bregman projections algorithm (or Sinkhorn-Knopp algorithm). The idea is to overrelax the Bregman projection operators, allowing for faster convergence. In practice this corresponds to elevating the diagonal scaling factors to a given power, at each step of the algorithm. We propose a simple method for establishing global convergence by ensuring the decrease of a Lyapunov function at each step. An adaptive choice of overrelaxation parameter based on the Lyapunov function is constructed. We also suggest a heuristic to choose a suitable asymptotic overrelaxation parameter, based on a local convergence analysis. Our numerical experiments show a gain in convergence speed by an order of magnitude in certain regimes.
dc.description.sponsorshipGeneralized Optimal Transport Models for Image processing - ANR-16-CE33-0010
dc.language.isoen
dc.title.enOverrelaxed Sinkhorn-Knopp Algorithm for Regularized Optimal Transport
dc.typeCommunication dans un congrès
dc.subject.halInformatique [cs]/Traitement du signal et de l'image
dc.subject.halMathématiques [math]/Optimisation et contrôle [math.OC]
dc.identifier.arxiv1711.01851
bordeaux.hal.laboratoriesInstitut de Mathématiques de Bordeaux (IMB) - UMR 5251*
bordeaux.institutionUniversité de Bordeaux
bordeaux.institutionBordeaux INP
bordeaux.institutionCNRS
bordeaux.conference.titleNIPS Workshop on Optimal Transport & Machine Learning (OTML'17)
bordeaux.countryUS
bordeaux.conference.cityLong Beach
bordeaux.peerReviewedoui
hal.identifierhal-01629985
hal.version1
hal.invitednon
hal.proceedingsoui
hal.popularnon
hal.audienceInternationale
hal.origin.linkhttps://hal.archives-ouvertes.fr//hal-01629985v1
bordeaux.COinSctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.au=THIBAULT,%20Alexis&CHIZAT,%20Lenaic&DOSSAL,%20Charles&PAPADAKIS,%20Nicolas&rft.genre=unknown


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