Central limit theorem for high temperature spin models via martingale embedding

Abstract

We use martingale embeddings to prove a central limit theorem (CLT) for one-dimensional projections of high-dimensional random vectors in $\{-1,1{\}}^n$ satisfying a Poincaré inequality. We obtain a non-asymptotic error bound involving two-point and three-point functions for the CLT in 2-Wasserstein distance. We present three illustrative applications: Ising model with finite-range interactions, ferromagnetic Ising model under the Dobrushin condition, and the Sherrington-Kirkpatrick spin glass model at sufficiently high temperature. In all the examples, we allow heterogeneous external fields.

v3: 39 pages. Added an application to the Sherrington-Kirkpatrick spin glass model. Added a coauthor