Improved covariance estimation: optimal robustness and sub-Gaussian guarantees under heavy tails

arXiv2209.13485MaRDI QIDQ6506670

Roberto I. Oliveira, Zoraida F. Rico

Abstract: We present an estimator of the covariance matrix $Sigma$ of random $d$-dimensional vector from an i.i.d. sample of size $n$. Our sole assumption is that this vector satisfies a bounded $L^p-L^2$ moment assumption over its one-dimensional marginals, for some $pgeq4$. Given this, we show that $Sigma$ can be estimated from the sample with the same high-probability error rates that the sample covariance matrix achieves in the case of Gaussian data. This holds even though we allow for very general distributions that may not have moments of order $>p$. Moreover, our estimator can be made to be optimally robust to adversarial contamination. This result improves recent results in the literature by Mendelson and Zhivotovskiy and Catoni and Giulini, and matches parallel work by Abdalla and Zhivotovskiy (the exact relationship with this last work is described in the paper).

This page was built for publication: Improved covariance estimation: optimal robustness and sub-Gaussian guarantees under heavy tails

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6506670)