{ "id": "0903.2323", "version": "v2", "published": "2009-03-13T07:09:30.000Z", "updated": "2009-08-27T16:22:41.000Z", "title": "Quantitative estimates of the convergence of the empirical covariance matrix in Log-concave Ensembles", "authors": [ "Radosław Adamczak", "Alexander E. Litvak", "Alain Pajor", "Nicole Tomczak-Jaegermann" ], "comment": "Exposition changed, several explanatory remarks added, some proofs simplified", "categories": [ "math.PR", "math.FA" ], "abstract": "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 $1-\\exp(-c\\sqrt n)$.", "revisions": [ { "version": "v2", "updated": "2009-08-27T16:22:41.000Z" } ], "analyses": { "subjects": [ "52A20", "46B09", "52A21", "15A52", "60E15" ], "keywords": [ "empirical covariance matrix", "log-concave ensembles", "quantitative estimates", "isotropic convex body", "convergence" ], "tags": [ "journal article" ], "publication": { "doi": "10.1090/S0894-0347-09-00650-X", "journal": "Journal of the American Mathematical Society", "year": 2010, "month": "Apr", "volume": 23, "number": 2, "pages": 535 }, "note": { "typesetting": "TeX", "pages": 0, "language": "en", "license": "arXiv", "status": "editable", "adsabs": "2010JAMS...23..535A" } } }