{ "id": "1010.3162", "version": "v1", "published": "2010-10-15T13:39:05.000Z", "updated": "2010-10-15T13:39:05.000Z", "title": "Uniform convergence of Vapnik--Chervonenkis classes under ergodic sampling", "authors": [ "Terrence M. Adams", "Andrew B. Nobel" ], "comment": "Published in at http://dx.doi.org/10.1214/09-AOP511 the Annals of Probability (http://www.imstat.org/aop/) by the Institute of Mathematical Statistics (http://www.imstat.org)", "journal": "Annals of Probability 2010, Vol. 38, No. 4, 1345-1367", "doi": "10.1214/09-AOP511", "categories": [ "math.PR" ], "abstract": "We show that if $\\mathcal{X}$ is a complete separable metric space and $\\mathcal{C}$ is a countable family of Borel subsets of $\\mathcal{X}$ with finite VC dimension, then, for every stationary ergodic process with values in $\\mathcal{X}$, the relative frequencies of sets $C\\in\\mathcal{C}$ converge uniformly to their limiting probabilities. Beyond ergodicity, no assumptions are imposed on the sampling process, and no regularity conditions are imposed on the elements of $\\mathcal{C}$. The result extends existing work of Vapnik and Chervonenkis, among others, who have studied uniform convergence for i.i.d. and strongly mixing processes. Our method of proof is new and direct: it does not rely on symmetrization techniques, probability inequalities or mixing conditions. The uniform convergence of relative frequencies for VC-major and VC-graph classes of functions under ergodic sampling is established as a corollary of the basic result for sets.", "revisions": [ { "version": "v1", "updated": "2010-10-15T13:39:05.000Z" } ], "analyses": { "keywords": [ "uniform convergence", "vapnik-chervonenkis classes", "ergodic sampling", "complete separable metric space", "result extends existing work" ], "tags": [ "journal article" ], "note": { "typesetting": "TeX", "pages": 0, "language": "en", "license": "arXiv", "status": "editable", "adsabs": "2010arXiv1010.3162A" } } }