Lower bounds on the smallest eigenvalue of a sample covariance matrix

Abstract

We derive tight lower bounds on the smallest eigenvalue of a sample covariance matrix of a centred isotropic random vector under weak or no assumptions on its components.

References in corpus (1)

• Covariance estimation for distributions with $2+\epsilon$ moments

Cited by in corpus (4)

• Exact minimax risk for linear least squares, and the lower tail of sample covariance matrices
• The smallest singular value of a shifted $d$-regular random square matrix
• Fast and Robust Sparsity Learning over Networks: A Decentralized Surrogate Median Regression Approach
• Estimating covariance and precision matrices along subspaces