Outlier-Robust Learning of Ising Models Under Dobrushin's Condition
Lists
Only you see this
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-$2$ polynomials of Ising models that may be of independent interest.
BibTeX
@inproceedings{diakonikolas2021outlier,
author = {Ilias Diakonikolas and Daniel M. Kane and Alistair Stewart and Yuxin Sun},
title = {{Outlier-Robust Learning of Ising Models Under Dobrushin's Condition}},
booktitle = {Conference on Learning Theory},
year = {2021},
url = {https://openreview.net/forum?id=pSP8X2kDDzh},
}