English

Learning Ising models from one or multiple samples

Statistics Theory 2020-12-11 v3 Machine Learning Statistics Theory

Abstract

There have been two separate lines of work on estimating Ising models: (1) estimating them from multiple independent samples under minimal assumptions about the model's interaction matrix; and (2) estimating them from one sample in restrictive settings. We propose a unified framework that smoothly interpolates between these two settings, enabling significantly richer estimation guarantees from one, a few, or many samples. Our main theorem provides guarantees for one-sample estimation, quantifying the estimation error in terms of the metric entropy of a family of interaction matrices. As corollaries of our main theorem, we derive bounds when the model's interaction matrix is a (sparse) linear combination of known matrices, or it belongs to a finite set, or to a high-dimensional manifold. In fact, our main result handles multiple independent samples by viewing them as one sample from a larger model, and can be used to derive estimation bounds that are qualitatively similar to those obtained in the afore-described multiple-sample literature. Our technical approach benefits from sparsifying a model's interaction network, conditioning on subsets of variables that make the dependencies in the resulting conditional distribution sufficiently weak. We use this sparsification technique to prove strong concentration and anti-concentration results for the Ising model, which we believe have applications beyond the scope of this paper.

Keywords

Cite

@article{arxiv.2004.09370,
  title  = {Learning Ising models from one or multiple samples},
  author = {Yuval Dagan and Constantinos Daskalakis and Nishanth Dikkala and Anthimos Vardis Kandiros},
  journal= {arXiv preprint arXiv:2004.09370},
  year   = {2020}
}
R2 v1 2026-06-23T14:58:13.118Z