Stability of Mean-Field Variational Inference

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sheng, Shunan, Wu, Bohan, González-Sanz, Alberto, Nutz, Marcel
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915333815664640
author Sheng, Shunan
Wu, Bohan
González-Sanz, Alberto
Nutz, Marcel
author_facet Sheng, Shunan
Wu, Bohan
González-Sanz, Alberto
Nutz, Marcel
contents Mean-field variational inference (MFVI) is a widely used method for approximating high-dimensional probability distributions by product measures. This paper studies the stability properties of the mean-field approximation when the target distribution varies within the class of strongly log-concave measures. We establish dimension-free Lipschitz continuity of the MFVI optimizer with respect to the target distribution, measured in the 2-Wasserstein distance, with Lipschitz constant inversely proportional to the log-concavity parameter. Under additional regularity conditions, we further show that the MFVI optimizer depends differentiably on the target potential and characterize the derivative by a partial differential equation. Methodologically, we follow a novel approach to MFVI via linearized optimal transport: the non-convex MFVI problem is lifted to a convex optimization over transport maps with a fixed base measure, enabling the use of calculus of variations and functional analysis. We discuss several applications of our results to robust Bayesian inference and empirical Bayes, including a quantitative Bernstein--von Mises theorem for MFVI, as well as to distributed stochastic control.
format Preprint
id arxiv_https___arxiv_org_abs_2506_07856
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Stability of Mean-Field Variational Inference
Sheng, Shunan
Wu, Bohan
González-Sanz, Alberto
Nutz, Marcel
Probability
Functional Analysis
Statistics Theory
Machine Learning
90C25, 49Q22, 62F15, 49N80
Mean-field variational inference (MFVI) is a widely used method for approximating high-dimensional probability distributions by product measures. This paper studies the stability properties of the mean-field approximation when the target distribution varies within the class of strongly log-concave measures. We establish dimension-free Lipschitz continuity of the MFVI optimizer with respect to the target distribution, measured in the 2-Wasserstein distance, with Lipschitz constant inversely proportional to the log-concavity parameter. Under additional regularity conditions, we further show that the MFVI optimizer depends differentiably on the target potential and characterize the derivative by a partial differential equation. Methodologically, we follow a novel approach to MFVI via linearized optimal transport: the non-convex MFVI problem is lifted to a convex optimization over transport maps with a fixed base measure, enabling the use of calculus of variations and functional analysis. We discuss several applications of our results to robust Bayesian inference and empirical Bayes, including a quantitative Bernstein--von Mises theorem for MFVI, as well as to distributed stochastic control.
title Stability of Mean-Field Variational Inference
topic Probability
Functional Analysis
Statistics Theory
Machine Learning
90C25, 49Q22, 62F15, 49N80
url https://arxiv.org/abs/2506.07856