Efficient Sampling for Ising and Potts Models using Auxiliary Gaussian Variables

TL;DR

This paper introduces an auxiliary Gaussian variable approach for sampling from Ising and Potts models, providing efficient algorithms with proven mixing time bounds and demonstrating competitive performance across various examples.

Contribution

The paper proposes a novel auxiliary Gaussian variable method for Ising and Potts models, including new scalable choices and mixing time analysis.

Findings

Mixing time bounds comparable to existing algorithms

Scalable auxiliary Gaussian choices for Potts models

Numerical results show competitive performance

Abstract

Ising and Potts models are an important class of discrete probability distributions which originated from statistical physics and since then have found applications in several disciplines. Simulation from these models is a well known challenging problem. In this paper, we study a class of Markov chain Monte Carlo algorithms, in which we introduce an auxiliary Gaussian variable such that, conditional on this variable, the discrete states are independent. This approach is broadly applicable to Ising and Potts models, including ones in which the coupling matrix admits negative entries, as in spin glass and Hopfield models. We focus on a block Gibbs sampler version of this algorithm, which alternates between sampling the auxiliary Gaussian and the discrete states, and derive mixing time bounds for a wide class of Ising/Potts models at both high and low temperatures, yielding results analogous to those derived for the Heat Bath and Swendsen-Wang algorithms. We present novel choices of auxiliary Gaussian variables which scale well with the number of states in the Potts model, and which can take advantage of the low rank structure of the coupling matrix, if any. Finally, we numerically evaluate the performance of the auxiliary Gaussian Gibbs sampler with several competing algorithms, across a range of examples.