Infinite-Task Learning with Vector-Valued RKHSs

Abstract : Machine learning has witnessed the tremendous success of solving tasks depending on a hyperparameter. While multi-task learning is celebrated for its capacity to solve jointly a finite number of tasks, learning a continuum of tasks for various loss functions is still a challenge. A promising approach, called Parametric Task Learning, has paved the way in the case of piecewise-linear loss functions. We propose a generic approach, called Infinite-Task Learning, to solve jointly a continuum of tasks via vector-valued RKHSs. We provide generalization guarantees to the suggested scheme and illustrate its efficiency in cost-sensitive classification, quantile regression and density level set estimation.
Type de document :
Pré-publication, Document de travail
19 pages, 5 figures, 2 tables. Preprint NIPS 2018. 2018
Liste complète des métadonnées
Contributeur : Romain Brault <>
Soumis le : vendredi 25 mai 2018 - 16:17:28
Dernière modification le : mardi 26 mars 2019 - 15:02:32

Lien texte intégral


  • HAL Id : hal-01800203, version 1
  • ARXIV : 1805.08809


Romain Brault, Alex Lambert, Zoltan Szabo, Maxime Sangnier, Florence D'Alché-Buc. Infinite-Task Learning with Vector-Valued RKHSs. 19 pages, 5 figures, 2 tables. Preprint NIPS 2018. 2018. 〈hal-01800203〉



Consultations de la notice