PAC-Bayesian aggregation of affine estimators

Abstract : Aggregating estimators using exponential weights depending on their risk performs well in expectation, but sadly not in probability. Considering exponential weights of a penalized risk is a way to overcome this issue. We focus on the fixed design regression framework with sub-Gaussian noise and provide penalties allowing to obtain oracle inequalities in deviation for the aggregation of affine estimators. Sharp oracle inequalities are provided by a condition using the regression function's norm. MSC 2010 subject classifications: Primary 62G08; secondary 62J02.
Type de document :
Pré-publication, Document de travail
2016
Liste complète des métadonnées

https://hal.inria.fr/hal-01070805
Contributeur : Erwan Le Pennec <>
Soumis le : lundi 24 octobre 2016 - 16:52:42
Dernière modification le : samedi 18 février 2017 - 01:20:07

Fichier

ArticlePAC_Arxiv.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Citation

Lucie Montuelle, Erwan Le Pennec. PAC-Bayesian aggregation of affine estimators. 2016. <hal-01070805v2>

Partager

Métriques

Consultations de
la notice

147

Téléchargements du document

101