Kalman-Langevin dynamics : exponential convergence, particle approximation and numerical approximation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ringh, Axel, Sharma, Akash
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909593995575296
author Ringh, Axel
Sharma, Akash
author_facet Ringh, Axel
Sharma, Akash
contents Langevin dynamics has found a large number of applications in sampling, optimization and estimation. Preconditioning the gradient in the dynamics with the covariance - an idea that originated in literature related to solving estimation and inverse problems using Kalman techniques - results in a mean-field (McKean-Vlasov) SDE. We demonstrate exponential convergence of the time marginal law of the mean-field SDE to the Gibbs measure with non-Gaussian potentials. This extends previous results, obtained in the Gaussian setting, to a broader class of potential functions. We also establish uniform in time bounds on all moments and convergence in $p$-Wasserstein distance. Furthermore, we show convergence of a weak particle approximation, that avoids computing the square root of the empirical covariance matrix, to the mean-field limit. Finally, we prove that an explicit numerical scheme for approximating the particle dynamics converges, uniformly in number of particles, to its continuous-time limit, addressing non-global Lipschitzness in the measure.
format Preprint
id arxiv_https___arxiv_org_abs_2504_18139
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Kalman-Langevin dynamics : exponential convergence, particle approximation and numerical approximation
Ringh, Axel
Sharma, Akash
Probability
Numerical Analysis
Statistics Theory
65C30, 60H35, 60H10, 37H10, 35Q84
Langevin dynamics has found a large number of applications in sampling, optimization and estimation. Preconditioning the gradient in the dynamics with the covariance - an idea that originated in literature related to solving estimation and inverse problems using Kalman techniques - results in a mean-field (McKean-Vlasov) SDE. We demonstrate exponential convergence of the time marginal law of the mean-field SDE to the Gibbs measure with non-Gaussian potentials. This extends previous results, obtained in the Gaussian setting, to a broader class of potential functions. We also establish uniform in time bounds on all moments and convergence in $p$-Wasserstein distance. Furthermore, we show convergence of a weak particle approximation, that avoids computing the square root of the empirical covariance matrix, to the mean-field limit. Finally, we prove that an explicit numerical scheme for approximating the particle dynamics converges, uniformly in number of particles, to its continuous-time limit, addressing non-global Lipschitzness in the measure.
title Kalman-Langevin dynamics : exponential convergence, particle approximation and numerical approximation
topic Probability
Numerical Analysis
Statistics Theory
65C30, 60H35, 60H10, 37H10, 35Q84
url https://arxiv.org/abs/2504.18139