Minimax optimality of the local multi-resolution projection estimator over Besov spaces

Abstract : The local multi-resolution projection estimator (LMPE) has been first introduced in Monnier, "Classification via local multi-resolution projections", EJS 2011 [Monnier2011]. It was proved there that plug-in classifiers built upon the LMPE can reach super-fast rates under a margin assumption. As a by-product, the LMPE was also proved to be near minimax optimal in the regression setting over a wide generalized Lipschitz (or Hölder) scale. In this paper, we show that a direct treatment of the regression loss allows to generalize the minimax optimality of the LMPE to a much wider Besov scale. To be more precise, we prove that the LMPE is near minimax optimal over Besov spaces $B^s_{\tau,q}$, $s >0$, $\tau \geq p$, $q>0$, when the loss is measured in $\Lp_p$-norm, $p \in [2,\infty)$ (see Theorem 2.1), and over Besov spaces $B^s_{\tau,q}$, $s > d/\tau$, $\tau, q >0$, when the loss is measured in $\Lp_{\infty}$-norm (see Theorem 2.2). Moreover, we show that an appropriate version of Lepski's method allows to make these results adaptive. Interestingly, all the proofs detailed here are largely different from the ones given in [Monnier2011].
Type de document :
Pré-publication, Document de travail
13 pages, 1 figure. 2012
Liste complète des métadonnées


https://hal.archives-ouvertes.fr/hal-00674091
Contributeur : Jean-Baptiste Monnier <>
Soumis le : jeudi 1 mars 2012 - 11:24:40
Dernière modification le : lundi 29 mai 2017 - 14:21:57
Document(s) archivé(s) le : jeudi 31 mai 2012 - 02:36:54

Fichier

localmultires-reg.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00674091, version 2

Collections

UPMC | USPC | PMA

Citation

Jean-Baptiste Monnier. Minimax optimality of the local multi-resolution projection estimator over Besov spaces. 13 pages, 1 figure. 2012. <hal-00674091v2>

Partager

Métriques

Consultations de
la notice

204

Téléchargements du document

76