Sharp Oracle Inequalities for Aggregation of Affine Estimators - École des Ponts ParisTech Access content directly
Journal Articles Annals of Statistics Year : 2012

Sharp Oracle Inequalities for 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 least square regression, kernel ridge regression, shrinking estimators and many other estimators 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.
Fichier principal
Vignette du fichier
affine_EWA_revision_hal.pdf (486.09 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-00587225 , version 1 (19-04-2011)
hal-00587225 , version 2 (26-04-2011)
hal-00587225 , version 3 (27-02-2012)

Identifiers

Cite

Arnak S. Dalalyan, Joseph Salmon. Sharp Oracle Inequalities for Aggregation of Affine Estimators. Annals of Statistics, 2012, 40 (4), pp.2327-2355. ⟨10.1214/12-AOS1038⟩. ⟨hal-00587225v3⟩
538 View
598 Download

Altmetric

Share

Gmail Facebook X LinkedIn More