Robustly Learning Mixtures of $k$ Arbitrary Gaussians
Abstract
We give a polynomial-time algorithm for the problem of robustly estimating a mixture of arbitrary Gaussians in , for any fixed , in the presence of a constant fraction of arbitrary corruptions. This resolves the main open problem in several previous works on algorithmic robust statistics, which addressed the special cases of robustly estimating (a) a single Gaussian, (b) a mixture of TV-distance separated Gaussians, and (c) a uniform mixture of two Gaussians. Our main tools are an efficient \emph{partial clustering} algorithm that relies on the sum-of-squares method, and a novel \emph{tensor decomposition} algorithm that allows errors in both Frobenius norm and low-rank terms.
Cite
@article{arxiv.2012.02119,
title = {Robustly Learning Mixtures of $k$ Arbitrary Gaussians},
author = {Ainesh Bakshi and Ilias Diakonikolas and He Jia and Daniel M. Kane and Pravesh K. Kothari and Santosh S. Vempala},
journal= {arXiv preprint arXiv:2012.02119},
year = {2021}
}
Comments
This version extends the previous one to yield 1) robust proper learning algorithm with poly(eps) error and 2) an information theoretic argument proving that the same algorithms in fact also yield parameter recovery guarantees. The updates are included in Sections 7,8, and 9 and the main result from the previous version (Thm 1.4) is presented and proved in Section 6