Saved in:
Bibliographic Details
Main Authors: Bianchi, Pascal, Hachem, Walid, Priser, Victor
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.17472
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916781435650048
author Bianchi, Pascal
Hachem, Walid
Priser, Victor
author_facet Bianchi, Pascal
Hachem, Walid
Priser, Victor
contents We consider a discrete-time system of n coupled random vectors, a.k.a. interacting particles. The dynamics involve a vanishing step size, some random centered perturbations, and a mean vector field which induces the coupling between the particles. We study the doubly asymptotic regime where both the number of iterations and the number n of particles tend to infinity, without any constraint on the relative rates of convergence of these two parameters. We establish that the empirical measure of the interpolated trajectories of the particles converges in probability, in an ergodic sense, to the set of recurrent Mc-Kean-Vlasov distributions. A first application example is the granular media equation, where the particles are shown to converge to a critical point of the Helmholtz energy. A second example is the convergence of stochastic gradient descent to the global minimizer of the risk, in a wide two-layer neural networks using random features.
format Preprint
id arxiv_https___arxiv_org_abs_2403_17472
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Long run convergence of discrete-time interacting particle systems of the McKean-Vlasov type
Bianchi, Pascal
Hachem, Walid
Priser, Victor
Probability
We consider a discrete-time system of n coupled random vectors, a.k.a. interacting particles. The dynamics involve a vanishing step size, some random centered perturbations, and a mean vector field which induces the coupling between the particles. We study the doubly asymptotic regime where both the number of iterations and the number n of particles tend to infinity, without any constraint on the relative rates of convergence of these two parameters. We establish that the empirical measure of the interpolated trajectories of the particles converges in probability, in an ergodic sense, to the set of recurrent Mc-Kean-Vlasov distributions. A first application example is the granular media equation, where the particles are shown to converge to a critical point of the Helmholtz energy. A second example is the convergence of stochastic gradient descent to the global minimizer of the risk, in a wide two-layer neural networks using random features.
title Long run convergence of discrete-time interacting particle systems of the McKean-Vlasov type
topic Probability
url https://arxiv.org/abs/2403.17472