22
5

A Concentration of Measure and Random Matrix Approach to Large Dimensional Robust Statistics

Abstract

This article studies the \emph{robust covariance matrix estimation} of a data collection X=(x1,,xn)X = (x_1,\ldots,x_n) with xi=τizi+mx_i = \sqrt \tau_i z_i + m, where ziRpz_i \in \mathbb R^p is a \textit{concentrated vector} (e.g., an elliptical random vector), mRpm\in \mathbb R^p a deterministic signal and τiR\tau_i\in \mathbb R a scalar perturbation of possibly large amplitude, under the assumption where both nn and pp are large. This estimator is defined as the fixed point of a function which we show is contracting for a so-called \textit{stable semi-metric}. We exploit this semi-metric along with concentration of measure arguments to prove the existence and uniqueness of the robust estimator as well as evaluate its limiting spectral distribution.

View on arXiv
Comments on this paper