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

Abstract

Let $K$ be an isotropic convex body in ${\mathbb{R}}^n$. Given $\eps>0$, how many independent points $X_i$ uniformly distributed on $K$ are needed for the empirical covariance matrix to approximate the identity up to $\eps$ with overwhelming probability? Our paper answers this question posed by Kannan, Lovasz and Simonovits. More precisely, let $X\in {\mathbb{R}}^n$ be a centered random vector with a log-concave distribution and with the identity as covariance matrix. An example of such a vector $X$ is a random point in an isotropic convex body. We show that for any $\eps>0$, there exists $C(\eps)>0$, such that if $N\sim C(\eps) n$ and $(X_i{)}_{i\le N}$ are i.i.d. copies of $X$, then $ \Big\|\frac{1}{N}\sum_{i=1}^N X_i\otimes X_i - \Id\Big\| \le ε, $ with probability larger than $1-\exp (-c\sqrt{n})$.

Exposition changed, several explanatory remarks added, some proofs simplified

Cited by in corpus (16)

• Covariance estimation for distributions with $2+\epsilon$ moments
• Convergence of the largest eigenvalue of normalized sample covariance matrices when p and n both tend to infinity with their ratio converging to zero
• Exact minimax risk for linear least squares, and the lower tail of sample covariance matrices
• A note on the Marchenko-Pastur law for a class of random matrices with dependent entries
• Random tensor theory: extending random matrix theory to random product states
• Almost sure convergence of the largest and smallest eigenvalues of high-dimensional sample correlation matrices
• On the convergence of the extremal eigenvalues of empirical covariance matrices with dependence
• Approximating the moments of marginals of high-dimensional distributions
• Moment estimates for convex measures
• The smallest singular value of a shifted $d$-regular random square matrix
• Covariance Matrix Estimation from Linearly-Correlated Gaussian Samples
• Bayesian inference for spectral projectors of the covariance matrix
• An efficiency upper bound for inverse covariance estimation
• Application of gradient descent algorithms based on geodesic distances
• Estimating covariance and precision matrices along subspaces
• Concentration and moment inequalities for sums of independent heavy-tailed random matrices