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

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

2009-03-13

arxiv.org/abs/0903.2323v2

Mathematics

Probability

Exposition changed, several explanatory remarks added, some proofs simplified

Scientific paper

Let $K$ be an isotropic convex body in $\R^n$. 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 $X\in\R^n$ 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 \epsilon, $ with probability larger than $1-\exp(-c\sqrt n)$.

Affiliated with

Also associated with

No associations

Rating

Quantitative estimates of the convergence of the empirical covariance matrix in Log-concave Ensembles does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Quantitative estimates of the convergence of the empirical covariance matrix in Log-concave Ensembles, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Quantitative estimates of the convergence of the empirical covariance matrix in Log-concave Ensembles will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-228401