Fast learning rates for plug-in classifiers under the margin condition - ParisTech Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2011

Fast learning rates for plug-in classifiers under the margin condition

Résumé

It has been recently shown that, under the margin (or low noise) assumption, there exist classifiers attaining fast rates of convergence of the excess Bayes risk, i.e., the rates faster than $n^{-1/2}$. The works on this subject suggested the following two conjectures: (i) the best achievable fast rate is of the order $n^{-1}$, and (ii) the plug-in classifiers generally converge slower than the classifiers based on empirical risk minimization. We show that both conjectures are not correct. In particular, we construct plug-in classifiers that can achieve not only the fast, but also the {\it super-fast} rates, i.e., the rates faster than $n^{-1}$. We establish minimax lower bounds showing that the obtained rates cannot be improved.
Fichier principal
Vignette du fichier
plugin_v3.pdf (355.42 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-00005882 , version 1 (08-07-2005)
hal-00005882 , version 2 (13-09-2005)
hal-00005882 , version 3 (24-05-2011)

Identifiants

Citer

Jean-Yves Audibert, Alexandre B. Tsybakov. Fast learning rates for plug-in classifiers under the margin condition. 2011. ⟨hal-00005882v3⟩
234 Consultations
356 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More