Statistical performance of support vector machines

Simple item page
dc.creatorBlanchard, Gilles
dc.creatorBousquet, Olivier
dc.creatorMassart, Pascal
dc.date2008-04-03
dc.date.accessioned2026-07-07T12:18:04Z
dc.date.available2026-07-07T12:18:04Z
dc.descriptionThe support vector machine (SVM) algorithm is well known to the computer learning community for its very good practical results. The goal of the present paper is to study this algorithm from a statistical perspective, using tools of concentration theory and empirical processes. Our main result builds on the observation made by other authors that the SVM can be viewed as a statistical regularization procedure. From this point of view, it can also be interpreted as a model selection principle using a penalized criterion. It is then possible to adapt general methods related to model selection in this framework to study two important points: (1) what is the minimum penalty and how does it compare to the penalty actually used in the SVM algorithm; (2) is it possible to obtain ``oracle inequalities'' in that setting, for the specific loss function used in the SVM algorithm? We show that the answer to the latter question is positive and provides relevant insight to the former. Our result shows that it is possible to obtain fast rates of convergence for SVMs.
dc.descriptionPublished in at http://dx.doi.org/10.1214/009053607000000839 the Annals of Statistics (http://www.imstat.org/aos/) by the Institute of Mathematical Statistics (http://www.imstat.org)
dc.identifierhttps://arxiv.org/abs/0804.0551
dc.identifierhttp://arxiv.org/abs/0804.0551
dc.identifierAnnals of Statistics 2008, Vol. 36, No. 2, 489-531
dc.identifierdoi:10.1214/009053607000000839
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/212285
dc.subjectStatistics Theory
dc.subject62G05, 62G20 (Primary)
dc.titleStatistical performance of support vector machines
dc.typetext

Files

Collections

arXiv