English

Sampling Approximately Low-Rank Ising Models: MCMC meets Variational Methods

Data Structures and Algorithms 2022-02-21 v1 Machine Learning Probability Machine Learning

Abstract

We consider Ising models on the hypercube with a general interaction matrix JJ, and give a polynomial time sampling algorithm when all but O(1)O(1) eigenvalues of JJ lie in an interval of length one, a situation which occurs in many models of interest. This was previously known for the Glauber dynamics when *all* eigenvalues fit in an interval of length one; however, a single outlier can force the Glauber dynamics to mix torpidly. Our general result implies the first polynomial time sampling algorithms for low-rank Ising models such as Hopfield networks with a fixed number of patterns and Bayesian clustering models with low-dimensional contexts, and greatly improves the polynomial time sampling regime for the antiferromagnetic/ferromagnetic Ising model with inconsistent field on expander graphs. It also improves on previous approximation algorithm results based on the naive mean-field approximation in variational methods and statistical physics. Our approach is based on a new fusion of ideas from the MCMC and variational inference worlds. As part of our algorithm, we define a new nonconvex variational problem which allows us to sample from an exponential reweighting of a distribution by a negative definite quadratic form, and show how to make this procedure provably efficient using stochastic gradient descent. On top of this, we construct a new simulated tempering chain (on an extended state space arising from the Hubbard-Stratonovich transform) which overcomes the obstacle posed by large positive eigenvalues, and combine it with the SGD-based sampler to solve the full problem.

Keywords

Cite

@article{arxiv.2202.08907,
  title  = {Sampling Approximately Low-Rank Ising Models: MCMC meets Variational Methods},
  author = {Frederic Koehler and Holden Lee and Andrej Risteski},
  journal= {arXiv preprint arXiv:2202.08907},
  year   = {2022}
}

Comments

43 pages

R2 v1 2026-06-24T09:43:26.276Z