Translator Disclaimer
2018 Decomposition of mean-field Gibbs distributions into product measures
Ronen Eldan, Renan Gross
Electron. J. Probab. 23(none): 1-24 (2018). DOI: 10.1214/18-EJP159

Abstract

We show that under a low complexity condition on the gradient of a Hamiltonian, Gibbs distributions on the Boolean hypercube are approximate mixtures of product measures whose probability vectors are critical points of an associated mean-field functional. This extends a previous work by the first author. As an application, we demonstrate how this framework helps characterize both Ising models satisfying a mean-field condition and the conditional distributions which arise in the emerging theory of nonlinear large deviations, both in the dense case and in the polynomially-sparse case.

Citation

Download Citation

Ronen Eldan. Renan Gross. "Decomposition of mean-field Gibbs distributions into product measures." Electron. J. Probab. 23 1 - 24, 2018. https://doi.org/10.1214/18-EJP159

Information

Received: 15 September 2017; Accepted: 20 March 2018; Published: 2018
First available in Project Euclid: 28 April 2018

zbMATH: 1390.60346
MathSciNet: MR3798245
Digital Object Identifier: 10.1214/18-EJP159

Subjects:
Primary: 05C80, 60F10, 60K35, 82B20

JOURNAL ARTICLE
24 PAGES


SHARE
Vol.23 • 2018
Back to Top