Show simple item record

hal.structure.identifierSchool of Mathematical Sciences [Shanghai]
dc.contributor.authorChen, Fan
hal.structure.identifierCEntre de REcherches en MAthématiques de la DEcision [CEREMADE]
dc.contributor.authorRen, Zhenjie
hal.structure.identifierCentre de Mathématiques Appliquées - Ecole Polytechnique [CMAP]
dc.contributor.authorWang, Songbo
dc.date.accessioned2023-01-16T13:56:54Z
dc.date.available2023-01-16T13:56:54Z
dc.date.issued2022
dc.identifier.urihttps://basepub.dauphine.psl.eu/handle/123456789/23740
dc.language.isoenen
dc.subject.ddc515en
dc.titleUniform-in-Time Propagation of Chaos for Mean Field Langevin Dynamicsen
dc.typeDocument de travail / Working paper
dc.description.abstractenWe study the uniform-in-time propagation of chaos for mean field Langevin dynamics with convex mean field potenital. Convergences in both Wasserstein-2 distance and relative entropy are established. We do not require the mean field potenital functional to bear either small mean field interaction or displacement convexity, which are common constraints in the literature. In particular, it allows us to study the efficiency of the noisy gradient descent algorithm for training two-layer neural networks.en
dc.publisher.cityParisen
dc.identifier.citationpages31en
dc.relation.ispartofseriestitleCahier de recherche CEREMADE, Université Paris Dauphine-PSLen
dc.subject.ddclabelAnalyseen
dc.identifier.citationdate2022
dc.description.ssrncandidatenon
dc.description.halcandidatenonen
dc.description.readershiprechercheen
dc.description.audienceInternationalen
dc.date.updated2023-01-16T13:43:14Z
hal.author.functionaut
hal.author.functionaut
hal.author.functionaut


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record