Optimal rates of aggregation in classification under low noise assumption

Simple item page
dc.creatorLecué, Guillaume
dc.date2006-03-18
dc.date2007-12-04
dc.date.accessioned2026-07-07T08:47:00Z
dc.date.available2026-07-07T08:47:00Z
dc.descriptionIn the same spirit as Tsybakov (2003), we define the optimality of an aggregation procedure in the problem of classification. Using an aggregate with exponential weights, we obtain an optimal rate of convex aggregation for the hinge risk under the margin assumption. Moreover we obtain an optimal rate of model selection aggregation under the margin assumption for the excess Bayes risk.
dc.identifierhttps://arxiv.org/abs/math/0603447
dc.identifierhttp://arxiv.org/abs/math/0603447
dc.identifierBernoulli 13, 4 (2007) 1000-1022
dc.identifierdoi:10.3150/07-BEJ6044
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/143449
dc.subjectStatistics Theory
dc.subject62G05, 62G20
dc.titleOptimal rates of aggregation in classification under low noise assumption
dc.typetext

Files

Collections

arXiv