Optimal oracle inequalities for model selection

dc.creatorMitchell, Charles
dc.creatorvan de Geer, Sara
dc.date2008-06-25
dc.date.accessioned2026-07-07T12:19:41Z
dc.date.available2026-07-07T12:19:41Z
dc.descriptionModel selection is often performed by empirical risk minimization. The quality of selection in a given situation can be assessed by risk bounds, which require assumptions both on the margin and the tails of the losses used. Starting with examples from the 3 basic estimation problems, regression, classification and density estimation, we formulate risk bounds for empirical risk minimization under successively weakening conditions and prove them at a very general level, for general margin and power tail behavior of the excess losses.
dc.descriptionSubmitted to the Electronic Journal of Statistics (http://www.i-journals.org/ejs/) by the Institute of Mathematical Statistics (http://www.imstat.org)
dc.identifierhttps://arxiv.org/abs/0806.4140
dc.identifierhttp://arxiv.org/abs/0806.4140
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/212841
dc.subjectStatistics Theory
dc.subject62G05 (Primary) 62G20 (Secondary)
dc.titleOptimal oracle inequalities for model selection
dc.typetext

Files

Collections