Can I read Robustly Learning Mixtures of $k$ Arbitrary Gaussians on EtoBox?

Robustly Learning Mixtures of $k$ Arbitrary Gaussians by Bakshi, Ainesh; Diakonikolas, Ilias; Jia, He; Kane, Daniel M.; Kothari, Pravesh K.; Vempala, Santosh S. is a scholarly article available to read on EtoBox.

What is Robustly Learning Mixtures of $k$ Arbitrary Gaussians about?

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 \emph{tensor decomposition} algorithm that allows errors in both Frobenius norm and low-rank terms.

Author

Bakshi, Ainesh; Diakonikolas, Ilias; Jia, He; Kane, Daniel M.; Kothari, Pravesh K.; Vempala, Santosh S.

Published

2020

Language

EN