Enregistré dans:
Détails bibliographiques
Auteurs principaux: Chen, Fan, Ren, Zhenjie, Wang, Songbo
Format: Preprint
Publié: 2022
Sujets:
Accès en ligne:https://arxiv.org/abs/2212.03050
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917061801803776
author Chen, Fan
Ren, Zhenjie
Wang, Songbo
author_facet Chen, Fan
Ren, Zhenjie
Wang, Songbo
contents We study the mean field Langevin dynamics and the associated particle system. By assuming the functional convexity of the energy, we obtain the $L^p$-convergence of the marginal distributions towards the unique invariant measure for the mean field dynamics. Furthermore, we prove the uniform-in-time propagation of chaos in both the $L^2$-Wasserstein metric and relative entropy.
format Preprint
id arxiv_https___arxiv_org_abs_2212_03050
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Uniform-in-time propagation of chaos for mean field Langevin dynamics
Chen, Fan
Ren, Zhenjie
Wang, Songbo
Probability
Machine Learning
60J60, 60K35 (Primary) 35B40, 35Q83, 35Q84 (Secondary)
We study the mean field Langevin dynamics and the associated particle system. By assuming the functional convexity of the energy, we obtain the $L^p$-convergence of the marginal distributions towards the unique invariant measure for the mean field dynamics. Furthermore, we prove the uniform-in-time propagation of chaos in both the $L^2$-Wasserstein metric and relative entropy.
title Uniform-in-time propagation of chaos for mean field Langevin dynamics
topic Probability
Machine Learning
60J60, 60K35 (Primary) 35B40, 35Q83, 35Q84 (Secondary)
url https://arxiv.org/abs/2212.03050