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

preprint2009arXivOpen access

Abstract

Let KK be an isotropic convex body in Rn\R^n. Given $\eps>0$, how many independent points XiX_i uniformly distributed on KK 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∈RnX\in\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 XX 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 (Xi)i≤N(X_i)_{i\le N} are i.i.d. copies of XX, then $ \Big\|\frac{1}{N}\sum_{i=1}^N X_i\otimes X_i - \Id\Big\| \le ε, $ with probability larger than 1−exp⁡(−cn)1-\exp(-c\sqrt n).

Explore this paper’s authors, topics and related work.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Reviews 0

Write a reviewWrite

No reviews yet.

Discussion 0

Add a commentWrite

No comments yet.