Online Multi-task Learning with Hard Constraints

Abstract : We discuss multi-task online learning when a decision maker has to deal simultaneously with M tasks. The tasks are related, which is modeled by imposing that the M-tuple of actions taken by the decision maker needs to satisfy certain constraints. We give natural examples of such restrictions and then discuss a general class of tractable constraints, for which we introduce computationally efficient ways of selecting actions, essentially by reducing to an on-line shortest path problem. We briefly discuss ``tracking'' and ``bandit'' versions of the problem and extend the model in various ways, including non-additive global losses and uncountably infinite sets of tasks.
Liste complète des métadonnées

Littérature citée [9 références]  Voir  Masquer  Télécharger
Contributeur : Gilles Stoltz <>
Soumis le : vendredi 20 mars 2009 - 14:05:44
Dernière modification le : mardi 2 avril 2019 - 14:15:59
Document(s) archivé(s) le : mercredi 22 septembre 2010 - 12:32:47


Fichiers produits par l'(les) auteur(s)


  • HAL Id : hal-00362643, version 2
  • ARXIV : 0902.3526



Gabor Lugosi, Omiros Papaspiliopoulos, Gilles Stoltz. Online Multi-task Learning with Hard Constraints. 2009. ⟨hal-00362643v2⟩



Consultations de la notice


Téléchargements de fichiers