Optimal aggregation of affine estimators

Abstract : We consider the problem of combining a (possibly uncountably infinite) set of affine estimators in non-parametric regression model with heteroscedastic Gaussian noise. Focusing on the exponentially weighted aggregate, we prove a PAC-Bayesian type inequality that leads to sharp oracle inequalities in discrete but also in continuous settings. The framework is general enough to cover the combinations of various procedures--such as the least square regression, the kernel ridge regression, the shrinkage estimators, etc.--used in the literature on statistical inverse problems. As a consequence, we show that the proposed aggregate provides an adaptive estimator in the exact minimax sense without neither discretizing the range of tuning parameters nor splitting the set of observations. We also illustrate numerically the good performance achieved by the exponentially weighted aggregate.
Type de document :
Communication dans un congrès
COLT - 24th Conference on Learning Theory - 2011, Jul 2011, Budapest, Hungary. 19 p., 2011
Liste complète des métadonnées

Contributeur : Arnak Dalalyan <>
Soumis le : mercredi 21 décembre 2011 - 13:58:27
Dernière modification le : lundi 29 mai 2017 - 14:21:31
Document(s) archivé(s) le : jeudi 22 mars 2012 - 02:26:24


Fichiers produits par l'(les) auteur(s)


  • HAL Id : hal-00654251, version 1



Joseph Salmon, Arnak S. Dalalyan. Optimal aggregation of affine estimators. COLT - 24th Conference on Learning Theory - 2011, Jul 2011, Budapest, Hungary. 19 p., 2011. <hal-00654251>



Consultations de
la notice


Téléchargements du document