The structure of low-complexity Gibbs measures on product spaces

DOI10.1214/19-AOP1352MaRDI QIDQ2189463zbMATH OpenFDO

Authors Tim Austin

Publication date 15 June 2020

Published in The Annals of Probability (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1810.07278, https://projecteuclid.org/euclid.aop/1575277346

zbMATH Keywords

Gibbs measuresnonlinear large deviationsdual total correlationgradient complexitymixtures of product measures

Mathematics Subject Classification ID

Optimal transportation (49Q22) Probability measures on topological spaces (60B05) Measures of information, entropy (94A17) Lattice systems (Ising, dimer, Potts, etc.) and systems on graphs arising in equilibrium statistical mechanics (82B20) Stochastic processes (60G99)

Abstract: Let $K_1$, $dots$, $K_n$ be bounded, complete, separable metric spaces. Let $lambd{a}_i$ be a Borel probability measure on $K_i$ for each $i$. Let $f:pro{d}_i{K}_{i}omathbbR$ be a bounded and continuous potential function, and let ${\displaystyle }$mu(d mathbf{x}) propto e^{f(mathbf{x})}lambda_1(d x_1)cdots lambda_n(d x_n)${\displaystyle }$ be the associated Gibbs distribution. At each point $mathbfxinpro{d}_i{K}_i$, one can define a `discrete gradient' $ablaf(mathbfx,,cdot,)$ by comparing the values of $f$ at all points which differ from $mathbfx$ in at most one coordinate. In case $pro{d}_i{K}_i={-1,1}^{n}subsetmathbb{R}^n$, the discrete gradient $ablaf(mathbfx,,cdot,)$ is naturally identified with a vector in $mathbb{R}^n$. This paper shows that a `low-complexity' assumption on $ablaf$ implies that $mu$ can be approximated by a mixture of other measures, relatively few in number, and most of them close to product measures in the sense of optimal transport. This implies also an approximation to the partition function of $f$ in terms of product measures, along the lines of Chatterjee and Dembo's theory of `nonlinear large deviations'. An important precedent for this work is a result of Eldan in the case $pro{d}_i{K}_i={-1,1}^n$. Eldan's assumption is that the discrete gradients $ablaf(mathbfx,,cdot,)$ all lie in a subset of $mathbb{R}^n$ that has small Gaussian width. His proof is based on the careful construction of a diffusion in $mathbb{R}^n$ which starts at the origin and ends with the desired distribution on the subset ${-1,1}^n$. Here our assumption is a more naive covering-number bound on the set of gradients $ablaf(mathbfx,,cdot,):mathbfxinpro{d}_i{K}_i$, and our proof relies only on basic inequalities of information theory. As a result, it is shorter, and applies to Gibbs measures on arbitrary product spaces.

Recommendations

• Gaussian-width gradient complexity, reverse log-Sobolev inequalities and nonlinear large deviations
• Decomposition of mean-field Gibbs distributions into product measures
• Quantitative approximate independence for continuous mean field Gibbs measures
• Stein's method for discrete Gibbs measures
• A transportation approach to the mean-field approximation

Cites work

• scientific article; zbMATH DE number 1158743 (Why is no real title available?)
• scientific article; zbMATH DE number 3202900 (Why is no real title available?)
• A simple proof of the blowing-up lemma (Corresp.)
• Bounding \(\bar d\)-distance by informational divergence: A method to prove measure concentration
• Concentration of measure and isoperimetric inequalities in product spaces
• Concentration of measure inequalities for Markov chains and \(\Phi\)-mixing processes.
• Decomposition of mean-field Gibbs distributions into product measures
• Elements of Information Theory
• Exponential random graphs behave like mixtures of stochastic block models
• Gaussian-width gradient complexity, reverse log-Sobolev inequalities and nonlinear large deviations
• I-divergence geometry of probability distributions and minimization problems
• Information inequalities and concentration of measure
• Large deviations for random graphs. École d'Été de Probabilités de Saint-Flour XLV -- 2015
• Linear dependence structure of the entropy space
• Measure concentration and the weak Pinsker property
• Measure concentration for a class of random processes
• Nonlinear large deviations
• Nonnegative entropy measures of multivariate symmetric correlations
• On the variational problem for upper tails in sparse random graphs
• Probability in Banach spaces. Isoperimetry and processes
• Real Analysis and Probability
• Transportation cost for Gaussian and other product measures
• Upper tails and independence polynomials in random graphs

Cited in

(16)

• Replica symmetry in upper tails of mean-field hypergraphs
• Large deviations of subgraph counts for sparse Erdős-Rényi graphs
• Nonlinear large deviation bounds with applications to Wigner matrices and sparse Erdős-Rényi graphs
• Gaussian-width gradient complexity, reverse log-Sobolev inequalities and nonlinear large deviations
• Decomposition of mean-field Gibbs distributions into product measures
• Spectral edge in sparse random graphs: upper and lower tail large deviations
• Upper tails via high moments and entropic stability
• Multi-variate correlation and mixtures of product measures.
• Upper Tail Large Deviations of Regular Subgraph Counts in Erdős‐Rényi Graphs in the Full Localized Regime
• Upper tail for homomorphism counts in constrained sparse random graphs
• Taming correlations through entropy-efficient measure decompositions with applications to mean-field approximation
• A transportation approach to the mean-field approximation
• A Dimension-Free Reverse Logarithmic Sobolev Inequality for Low-Complexity Functions in Gaussian Space
• Nonlinear large deviations: beyond the hypercube
• Large deviations for the largest eigenvalue of Gaussian networks with constant average degree
• Upper tail of the spectral radius of sparse Erdös-Rényi graphs

This page was built for publication: The structure of low-complexity Gibbs measures on product spaces

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2189463)