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

Abstract

We study the minimal sample size N=N(n) that suffices to estimate the covariance matrix of an n-dimensional distribution by the sample covariance matrix in the operator norm, with an arbitrary fixed accuracy. We establish the optimal bound N=O(n) for every distribution whose k-dimensional marginals have uniformly bounded $2+\epsilon$ moments outside the sphere of radius $O(\sqrt{k})$. In the specific case of log-concave distributions, this result provides an alternative approach to the Kannan-Lovasz-Simonovits problem, which was recently solved by Adamczak et al. [J. Amer. Math. Soc. 23 (2010) 535-561]. Moreover, a lower estimate on the covariance matrix holds under a weaker assumption - uniformly bounded $2+\epsilon$ moments of one-dimensional marginals. Our argument consists of randomizing the spectral sparsifier, a deterministic tool developed recently by Batson, Spielman and Srivastava [SIAM J. Comput. 41 (2012) 1704-1721]. The new randomized method allows one to control the spectral edges of the sample covariance matrix via the Stieltjes transform evaluated at carefully chosen random points.

Published in at http://dx.doi.org/10.1214/12-AOP760 the Annals of Probability (http://www.imstat.org/aop/) by the Institute of Mathematical Statistics (http://www.imstat.org)

References in corpus (1)

• Quantitative estimates of the convergence of the empirical covariance matrix in Log-concave Ensembles

Cited by in corpus (11)

• Structured Random Matrices
• Exact minimax risk for linear least squares, and the lower tail of sample covariance matrices
• Generalized Canonical Correlation Analysis for Classification
• Almost sure convergence of the largest and smallest eigenvalues of high-dimensional sample correlation matrices
• Lower bounds on the smallest eigenvalue of a sample covariance matrix
• On the convergence of the extremal eigenvalues of empirical covariance matrices with dependence
• The smallest singular value of a shifted $d$-regular random square matrix
• The relative effects of dimensionality and multiplicity of hypotheses on the F-test in linear regression
• Covariance Matrix Estimation from Linearly-Correlated Gaussian Samples
• Estimating covariance and precision matrices along subspaces
• Concentration and moment inequalities for sums of independent heavy-tailed random matrices