The reviewed record of science sign in
Pith

arxiv: 2402.07355 · v4 · pith:HYED76TS · submitted 2024-02-12 · math.ST · cs.LG· stat.ML· stat.TH

Sampling from the Mean-Field Stationary Distribution

Reviewed by Pithpith:HYED76TSopen to challenge →

classification math.ST cs.LGstat.MLstat.TH
keywords mean-fielddistributionstationarysamplingcomplexityfinite-particleguaranteesalgorithms
0
0 comments X
read the original abstract

We study the complexity of sampling from the stationary distribution of a mean-field SDE, or equivalently, the complexity of minimizing a functional over the space of probability measures which includes an interaction term. Our main insight is to decouple the two key aspects of this problem: (1) approximation of the mean-field SDE via a finite-particle system, via uniform-in-time propagation of chaos, and (2) sampling from the finite-particle stationary distribution, via standard log-concave samplers. Our approach is conceptually simpler and its flexibility allows for incorporating the state-of-the-art for both algorithms and theory. This leads to improved guarantees in numerous settings, including better guarantees for optimizing certain two-layer neural networks in the mean-field regime. A key technical contribution is to establish a new uniform-in-$N$ log-Sobolev inequality for the stationary distribution of the mean-field Langevin dynamics.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Uniform-in-Time Weak Propagation-of-Chaos in Shallow Neural Networks

    stat.ML 2026-05 unverdicted novelty 7.0

    Finite-width shallow networks remain within poly(d) m^{-min(1,c/6)} of their mean-field limit uniformly in time when mean-field excess loss decays as t^{-c} under standard regularity and an integral condition on the loss.