List-Decodable Robust Mean Estimation and Learning Mixtures of Spherical Gaussians
STOC '18: Symposium on Theory of Computing Los Angeles CA USA June, 2018, pp. 1047-1060, 2018.
We study the problem of list-decodable (robust) Gaussian mean estimation and the related problem of learning mixtures of separated spherical Gaussians. In the former problem, we are given a set T of points in n with the promise that an α-fraction of points in T, where 0< α < 1/2, are drawn from an unknown mean identity covariance Gaussian...More
Full Text (Upload PDF)
PPT (Upload PPT)