English

Outlier-Robust Learning of Ising Models Under Dobrushin's Condition

Machine Learning 2021-02-04 v1 Data Structures and Algorithms Probability Statistics Theory Machine Learning Statistics Theory

Abstract

We study the problem of learning Ising models satisfying Dobrushin's condition in the outlier-robust setting where a constant fraction of the samples are adversarially corrupted. Our main result is to provide the first computationally efficient robust learning algorithm for this problem with near-optimal error guarantees. Our algorithm can be seen as a special case of an algorithm for robustly learning a distribution from a general exponential family. To prove its correctness for Ising models, we establish new anti-concentration results for degree-22 polynomials of Ising models that may be of independent interest.

Keywords

Cite

@article{arxiv.2102.02171,
  title  = {Outlier-Robust Learning of Ising Models Under Dobrushin's Condition},
  author = {Ilias Diakonikolas and Daniel M. Kane and Alistair Stewart and Yuxin Sun},
  journal= {arXiv preprint arXiv:2102.02171},
  year   = {2021}
}
R2 v1 2026-06-23T22:48:28.289Z