Mean field approximations via log-concavity

arXiv2206.01260MaRDI QIDQ6400972FDOQ6400972

Authors: Daniel Lacker, Sumit Mukherjee, Lane Chun Yeung 

Publication date: 2 June 2022

Abstract: We propose a new approach to deriving quantitative mean field approximations for any probability measure $P$ on $mathbb{R}^n$ with density proportional to $e^{f(x)}$, for $f$ strongly concave. We bound the mean field approximation for the log partition function $logint{e}^{f(x)}dx$ in terms of $su{m}_{ieqj}mathbb{E}_{Q^{*}}|partia{l}_{ij}f{|}^2$, for a semi-explicit probability measure $Q^{*}$ characterized as the unique mean field optimizer, or equivalently as the minimizer of the relative entropy $H(cdot,|,P)$ over product measures. This notably does not involve metric-entropy or gradient-complexity concepts which are common in prior work on nonlinear large deviations. Three implications are discussed, in the contexts of continuous Gibbs measures on large graphs, high-dimensional Bayesian linear regression, and the construction of decentralized near-optimizers in high-dimensional stochastic control problems. Our arguments are based primarily on functional inequalities and the notion of displacement convexity from optimal transport.

Mathematics Subject Classification ID

Large deviations (60F10) Functional inequalities, including subadditivity, convexity, etc. (39B62)

This page was built for publication: Mean field approximations via log-concavity

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6400972)