Skip to Main content Skip to Navigation

Apprentissage statistique multi-tâches

Matthieu Solnon 1, 2
2 SIERRA - Statistical Machine Learning and Parsimony
DI-ENS - Département d'informatique de l'École normale supérieure, Inria Paris-Rocquencourt, CNRS - Centre National de la Recherche Scientifique : UMR8548
Abstract : This thesis aims at constructing, calibrating and studying multi-task estimators, in a frequentist non-parametric and non-asymptotic framework. We consider here kernel ridge regression and extend the existing multi-task regression methods in this setting. The main question is the calibration of a matricial regularization parameter, which encodes the similarity between the tasks. We propose a method to calibrate this parameter, based on the estimation of the covariance matrix of the noise between tasks. We then show optimality guarantees for the estimator thus obtained, via an oracle inequality. We also check its behaviour on simulated examples. We carefully bound the risks of both multi-task and single-task oracle estimators in some specific settings. This allows us to discern several interesting situations, whether the multi-task oracle outperforms the single-task one or not. This ensure the oracle inequality enforces the multi-task oracle to have a lower risk than the single-task one in the studied settings. Finally, we check the behaviour of the oracles on simulated examples.
Complete list of metadata
Contributor : Matthieu Solnon <>
Submitted on : Friday, November 29, 2013 - 12:00:02 PM
Last modification on : Friday, February 12, 2021 - 9:22:04 AM
Long-term archiving on: : Monday, March 3, 2014 - 7:41:30 PM


  • HAL Id : tel-00911498, version 1


Matthieu Solnon. Apprentissage statistique multi-tâches. Théorie [stat.TH]. Université Pierre et Marie Curie - Paris VI, 2013. Français. ⟨tel-00911498⟩



Record views


Files downloads