About cookies on this site Our websites require some cookies to function properly (required). In addition, other cookies may be used with your consent to analyze site usage, improve the user experience and for advertising. For more information, please review your options. By visiting our website, you agree to our processing of information as described in IBM’sprivacy statement. To provide a smooth navigation, your cookie preferences will be shared across the IBM web domains listed here.
Publication
NeurIPS 2023
Conference paper
A Spectral Algorithm for List-Decodable Covariance Estimation in Relative Frobenius Norm
Abstract
We study the problem of list-decodable Gaussian covariance estimation. Given a multiset of points in such that an unknown fraction of points in are i.i.d. samples from an unknown Gaussian , the goal is to output a list of hypotheses at least one of which is close to in relative Frobenius norm. Our main result is a sample and time algorithm for this task that guarantees relative Frobenius norm error of . Importantly, our algorithm relies purely on spectral techniques. As a corollary, we obtain an efficient spectral algorithm for robust partial clustering of Gaussian mixture models (GMMs) --- a key ingredient in the recent work of [BakDJKKV22] on robustly learning arbitrary GMMs. Combined with the other components of [BakDJKKV22], our new method yields the first Sum-of-Squares-free algorithm for robustly learning GMMs, resolving an open problem proposed by Vempala and Kothari. At the technical level, we develop a novel multi-filtering method for list-decodable covariance estimation that may be useful in other settings.