Saved in:
Bibliographic Details
Main Authors: Du, Kai, Ren, Zhenjie, Suciu, Florin, Wang, Songbo
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2311.11428
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908623426289664
author Du, Kai
Ren, Zhenjie
Suciu, Florin
Wang, Songbo
author_facet Du, Kai
Ren, Zhenjie
Suciu, Florin
Wang, Songbo
contents For a certain class of McKean-Vlasov processes, we introduce proxy processes that substitute the mean-field interaction with self-interaction, employing a weighted occupation measure. Our study encompasses two key achievements. First, we demonstrate the ergodicity of the self-interacting dynamics, under broad conditions, by applying the reflection coupling method. Second, in scenarios where the drifts are negative intrinsic gradients of convex mean-field potential functionals, we use entropy and functional inequalities to demonstrate that the stationary measures of the self-interacting processes approximate the invariant measures of the corresponding McKean-Vlasov processes. As an application, we show how to learn the optimal weights of a two-layer neural network by training a single neuron.
format Preprint
id arxiv_https___arxiv_org_abs_2311_11428
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Self-interacting approximation to McKean-Vlasov long-time limit: a Markov chain Monte Carlo method
Du, Kai
Ren, Zhenjie
Suciu, Florin
Wang, Songbo
Probability
For a certain class of McKean-Vlasov processes, we introduce proxy processes that substitute the mean-field interaction with self-interaction, employing a weighted occupation measure. Our study encompasses two key achievements. First, we demonstrate the ergodicity of the self-interacting dynamics, under broad conditions, by applying the reflection coupling method. Second, in scenarios where the drifts are negative intrinsic gradients of convex mean-field potential functionals, we use entropy and functional inequalities to demonstrate that the stationary measures of the self-interacting processes approximate the invariant measures of the corresponding McKean-Vlasov processes. As an application, we show how to learn the optimal weights of a two-layer neural network by training a single neuron.
title Self-interacting approximation to McKean-Vlasov long-time limit: a Markov chain Monte Carlo method
topic Probability
url https://arxiv.org/abs/2311.11428