Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

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.
Document type :
Preprints, Working Papers, ...
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01800203
Contributor : Romain Brault <>
Submitted on : Friday, May 25, 2018 - 4:17:28 PM
Last modification on : Wednesday, June 24, 2020 - 4:19:37 PM

Links full text

Identifiers

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

Citation

Romain Brault, Alex Lambert, Zoltan Szabo, Maxime Sangnier, Florence d'Alché-Buc. Infinite-Task Learning with Vector-Valued RKHSs. 2018. ⟨hal-01800203⟩

Share

Metrics

Record views

579