Optimal aggregation of affine estimators - École des Ponts ParisTech Access content directly
Conference Papers Year : 2011

Optimal aggregation of affine estimators


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.
Fichier principal
Vignette du fichier
COLT11a.pdf (334.67 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-00654251 , version 1 (21-12-2011)


  • 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. ⟨hal-00654251⟩
318 View
126 Download


Gmail Facebook X LinkedIn More