Tyler's and Maronna's M-estimators: Non-Asymptotic Concentration Results

Abstract

Tyler's and Maronna's M-estimators, as well as their regularized variants, are popular robust methods to estimate the scatter or covariance matrix of a multivariate distribution. In this work, we study the non-asymptotic behavior of these estimators, for data sampled from a distribution that satisfies one of the following properties: 1) independent sub-Gaussian entries, up to a linear transformation; 2) log-concave distributions; 3) distributions satisfying a convex concentration property. Our main contribution is the derivation of tight non-asymptotic concentration bounds of these M-estimators around a suitably scaled version of the data sample covariance matrix. Prior to our work, non-asymptotic bounds were derived only for Elliptical and Gaussian distributions. Our proof uses a variety of tools from non asymptotic random matrix theory and high dimensional geometry. Finally, we illustrate the utility of our results on two examples of practical interest: sparse covariance and sparse precision matrix estimation.

References in corpus (9)

• Covariance regularization by thresholding
• High-Breakdown Robust Multivariate Methods
• Optimal rates of convergence for sparse covariance matrix estimation
• Regularized $M$-estimators of scatter matrix
• Recent Advances in Algorithmic High-Dimensional Robust Statistics
• Regularized Tyler's Scatter Estimator: Existence, Uniqueness, and Algorithms
• Robust Estimation of Covariance Matrices: Adversarial Contamination and Beyond
• A Concentration of Measure and Random Matrix Approach to Large Dimensional Robust Statistics
• On Dimension-dependent concentration for convex Lipschitz functions in product spaces