Saved in:
Bibliographic Details
Main Authors: Germain, Pierre, Monmarché, Pierre
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.07448
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912370794692608
author Germain, Pierre
Monmarché, Pierre
author_facet Germain, Pierre
Monmarché, Pierre
contents For optimizing a non-convex function in finite dimension, a method is to add Brownian noise to a gradient descent, allowing for transitions between basins of attractions of different minimizers. To adapt this for optimization over a space of probability distributions requires a suitable noise. For this purpose, we introduce here a simple stochastic process where a number of moments of the distribution are following a chosen finite-dimensional diffusion process, generalizing some previous studies where the expectation of the measure is subject to a Brownian noise. The process may explode in finite time, for instance when trying to force the variance of a distribution to behave like a Brownian motion. We show, up to the possible explosion time, well-posedness and propagation of chaos for the system of mean-field interacting particles with common noise approximating the process.
format Preprint
id arxiv_https___arxiv_org_abs_2505_07448
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Stochastic moments dynamics: a flexible finite-dimensional random perturbation of Wasserstein gradient descent
Germain, Pierre
Monmarché, Pierre
Probability
For optimizing a non-convex function in finite dimension, a method is to add Brownian noise to a gradient descent, allowing for transitions between basins of attractions of different minimizers. To adapt this for optimization over a space of probability distributions requires a suitable noise. For this purpose, we introduce here a simple stochastic process where a number of moments of the distribution are following a chosen finite-dimensional diffusion process, generalizing some previous studies where the expectation of the measure is subject to a Brownian noise. The process may explode in finite time, for instance when trying to force the variance of a distribution to behave like a Brownian motion. We show, up to the possible explosion time, well-posedness and propagation of chaos for the system of mean-field interacting particles with common noise approximating the process.
title Stochastic moments dynamics: a flexible finite-dimensional random perturbation of Wasserstein gradient descent
topic Probability
url https://arxiv.org/abs/2505.07448