Robustly Learning Mixtures of $k$ Arbitrary Gaussians
Authors:
- Ainesh BakshiABAinesh Bakshi
- Ilias DiakonikolasIDIlias Diakonikolas
- He JiaHJHe Jia
- Daniel M. KaneDKDaniel M. Kane
- Pravesh K. KothariPKPravesh K. Kothari
- Santosh S. VempalaSVSantosh S. Vempala
Preprint
Abstract
We give a polynomial-time algorithm for the problem of robustly estimating a mixture of $k$ arbitrary Gaussians in $\mathbb{R}^d$, for any fixed $k$, 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 tensor decomposition algorithm that allows errors in both Frobenius norm and low-rank terms.