Show simple item record

dc.contributor.authorCuturi, Marco
dc.contributor.authorPeyré, Gabriel
dc.date.accessioned2017-11-22T13:41:59Z
dc.date.available2017-11-22T13:41:59Z
dc.date.issued2015
dc.identifier.issn1936-4954
dc.identifier.urihttps://basepub.dauphine.fr/handle/123456789/17019
dc.language.isoenen
dc.subjectconvex optimization
dc.subjectWasserstein
dc.subjectentropy
dc.subjectOptimal transport
dc.subject.ddc621.3en
dc.titleA Smoothed Dual Approach for Variational Wasserstein Problems
dc.typeArticle accepté pour publication ou publié
dc.description.abstractenVariational problems that involve Wasserstein distances have been recently proposed to summarize and learn from probability measures. Despite being conceptually simple, such problems are computationally challenging because they involve minimizing over quantities (Wasserstein distances) that are themselves hard to compute. We show that the dual formulation of Wasserstein variational problems introduced recently by Carlier et al. (2014) can be regularized using an entropic smoothing, which leads to smooth, differentiable, convex optimization problems that are simpler to implement and numerically more stable. We illustrate the versatility of this approach by applying it to the computation of Wasserstein barycenters and gradient flows of spacial regularization functionals.
dc.relation.isversionofjnlnameSIAM Journal on Imaging Sciences
dc.relation.isversionofjnlvol9
dc.relation.isversionofjnlissue1
dc.relation.isversionofjnldate2015
dc.relation.isversionofjnlpages320-343
dc.relation.isversionofdoi10.1137/15M1032600
dc.relation.isversionofjnlpublisherSociety for Industrial and Applied Mathematics
dc.subject.ddclabelTraitement du signalen
dc.relation.forthcomingnonen
dc.relation.forthcomingprintnonen
dc.description.ssrncandidatenon
dc.description.halcandidatenon
dc.description.readershiprecherche
dc.description.audienceInternational
dc.relation.Isversionofjnlpeerreviewedoui
dc.date.updated2017-12-20T15:09:13Z
hal.person.labIds409737
hal.person.labIds60


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record