Year: 2016
Type: conference-paper
Abstract: We consider the problem of estimating the mean and covariance of a distribution from i.i.d. samples in the presence of a fraction of malicious noise. This is in contrast to much recent work where the noise itself is assumed to be from a distribution of known type. The agnostic problem includes many interesting special cases, e.g., learning the parameters of a single Gaussian (or finding the best-fit Gaussian) when a fraction of data is adversarially corrupted, agnostically learning mixtures, agnostic ICA, etc. We present polynomial-time algorithms to estimate the mean and covariance with error guarantees in terms of information-theoretic lower bounds. As a corollary, we also obtain an agnostic algorithm for Singular Value Decomposition.
DOI: 10.1109/focs.2016.76
Authors: Kevin A. Lai, Anup B. Rao, Santosh Vempala
Institutions: Georgia Institute of Technology, Princeton University
Language: English
Subfield: Statistics and Probability
Field: Mathematics
Domain: Physical Sciences
Open Access status: green
Funder: National Science Foundation
OpenAlex ID: W2464464020
