Taming correlations through entropy-efficient measure decompositions with applications to mean-field approximation

DOI10.1007/s00440-019-00924-2zbMath1436.82016arXiv1811.11530OpenAlexW2950265730WikidataQ127752379 ScholiaQ127752379MaRDI QIDQ2174660

Ronen Eldan

Publication date: 21 April 2020

Published in: Probability Theory and Related Fields (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1811.11530

Mathematics Subject Classification ID

Geometric probability and stochastic geometry (60D05) Interacting particle systems in time-dependent statistical mechanics (82C22) Interacting random processes; statistical mechanics type models; percolation theory (60K35) Applications of stochastic analysis (to PDEs, etc.) (60H30) Dynamic lattice systems (kinetic Ising, etc.) and systems on graphs in time-dependent statistical mechanics (82C20)

Related Items (5)

Fluctuations in mean-field Ising models ⋮ Analysis of high-dimensional distributions using pathwise methods ⋮ A transportation approach to the mean-field approximation ⋮ Log concavity and concentration of Lipschitz functions on the Boolean hypercube ⋮ The Cut Metric for Probability Distributions

Cites Work

• Unnamed Item
• Unnamed Item
• Skorokhod embeddings via stochastic flows on the space of Gaussian measures
• Gaussian-width gradient complexity, reverse log-Sobolev inequalities and nonlinear large deviations
• Information-theoretic thresholds from the cavity method
• Bethe states of random factor graphs
• Decomposition of mean-field Gibbs distributions into product measures
• A transportation approach to the mean-field approximation
• The structure of low-complexity Gibbs measures on product spaces
• The CLT in high dimensions: quantitative bounds via martingale embedding
• Universality of the mean-field for the Potts model
• Thin shell implies spectral gap up to polylog via a stochastic localization scheme
• Factor models on locally tree-like graphs
• Nonlinear large deviations
• Harnessing the Bethe free energy
• Mean-field approximation, convex hierarchies, and the optimality of correlation rounding: a unified perspective

This page was built for publication: Taming correlations through entropy-efficient measure decompositions with applications to mean-field approximation