Bandwidth selection in kernel empirical risk minimization via the gradient - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2014

Bandwidth selection in kernel empirical risk minimization via the gradient

Résumé

In this paper, we deal with the data-driven selection of multidimensional and (possibly) anisotropic bandwidths in the general problem of kernel empirical risk minimization. We propose a universal selection rule, which leads to optimal adaptive results in a large variety of statistical models such as nonparametric regression or statistical learning with errors-in-variables. These results are stated in the context of smooth loss functions, where the gradient of the risk appears as a good criterion to measure the performance of our estimators. This turns out to be helpful to derive excess risk bounds - with fast rates of convergence - in noisy clustering as well as adaptive minimax results for pointwise and global estimation in robust nonparametric regression. The selection rule consists of a comparison of the gradient empirical risks. It can be viewed as a non-trivial improvement of the so-called GL method (Goldenshluger and Lepski, 2011) to non-linear estimators. Another main advantage of our selection rule is the non-dependency on the smallest eigenvalue of the Hessian matrix of the risk, which is a changing and unknown parameter determined by the underlying model.
Fichier principal
Vignette du fichier
glerc.pdf (577.5 Ko) Télécharger le fichier
Origine Fichiers éditeurs autorisés sur une archive ouverte
Loading...

Dates et versions

hal-00937026 , version 1 (30-01-2014)

Identifiants

  • HAL Id : hal-00937026 , version 1

Citer

Michaël Chichignoud, Sébastien Loustau. Bandwidth selection in kernel empirical risk minimization via the gradient. 2014. ⟨hal-00937026⟩
322 Consultations
161 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More