Comparison bewteen multi-task and single-task oracle risks in kernel ridge regression - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2013

Comparison bewteen multi-task and single-task oracle risks in kernel ridge regression

Résumé

In this paper we study multi-task kernel ridge regression and try to understand when the multi-task procedure performs better than the single-task one, in terms of averaged quadratic risk. In order to do so, we compare the risks of the estimators with perfect calibration, the \emph{oracle risk}. We are able to give explicit settings, favorable to the multi-task procedure, where the multi-task oracle performs better than the single-task one. In situations where the multi-task procedure is conjectured to perform badly, we also show the oracle does so. We then complete our study with simulated examples, where we can compare both oracle risks in more natural situations. A consequence of our result is that the multi-task ridge estimator has a lower risk than any single-task estimator, in favorable situations.
Fichier principal
Vignette du fichier
solnon_comparison.pdf (489.06 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00846715 , version 1 (19-07-2013)

Identifiants

Citer

Matthieu Solnon. Comparison bewteen multi-task and single-task oracle risks in kernel ridge regression. 2013. ⟨hal-00846715⟩
170 Consultations
101 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More