Square Root Penalty: Adaptation to the Margin in Classification and in Edge Estimation

Simple item page
dc.creatorTsybakov, A. B.
dc.creatorvan de Geer, S. A.
dc.date2005-07-21
dc.date.accessioned2026-07-07T08:07:04Z
dc.date.available2026-07-07T08:07:04Z
dc.descriptionWe consider the problem of adaptation to the margin in binary classification. We suggest a penalized empirical risk minimization classifier that adaptively attains, up to a logarithmic factor, fast optimal rates of convergence for the excess risk, that is, rates that can be faster than n^{-1/2}, where n is the sample size. We show that our method also gives adaptive estimators for the problem of edge estimation.
dc.descriptionPublished at http://dx.doi.org/10.1214/009053604000001066 in the Annals of Statistics (http://www.imstat.org/aos/) by the Institute of Mathematical Statistics (http://www.imstat.org)
dc.identifierhttps://arxiv.org/abs/math/0507422
dc.identifierhttp://arxiv.org/abs/math/0507422
dc.identifierAnnals of Statistics 2005, Vol. 33, No. 3, 1203-1224
dc.identifierdoi:10.1214/009053604000001066
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/130818
dc.subjectStatistics Theory
dc.subject62G07, 62G08, 62H30, 68T10 (Primary)
dc.titleSquare Root Penalty: Adaptation to the Margin in Classification and in Edge Estimation
dc.typetext

Files

Collections

arXiv