 |
|
|
|
| HAL : hal-00362643, version 2 |
| arXiv : 0902.3526 |
| Fiche détaillée |  Récupérer au format |
|
|
| Versions disponibles : | v1 (20-02-2009) | v2 (27-03-2009) |
|
|
|
|
| Online Multi-task Learning with Hard Constraints |
|
|
| Gabor Lugosi 1Omiros Papaspiliopoulos 1 |
|
|
| (13/02/2009) |
|
|
|
| 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. |
|
|
|
|
|
|
|
|
|
|
|
| 1 : | Institució Catalana de Recerca i Estudis Avançats [Barcelona] (ICREA) |
|
|
|
ICREA – Universitat de Barcelona – Fundació Catalana per a la Recerca i la Innovació (FCRI) |
|
|
| 2 : | Département de Mathématiques et Applications (DMA) |
|
|
|
CNRS : UMR8553 – Ecole Normale Supérieure de Paris - ENS Paris |
|
|
| 3 : | Groupement de Recherche et d'Etudes en Gestion à HEC (GREGH) |
|
|
|
GROUPE HEC – CNRS : UMR2959 |
|
|
|
|
|
|
|
|
|
| Domaine | : | Statistiques/Machine Learning Statistiques/Théorie Mathématiques/Statistiques Statistiques/Autres Informatique/Apprentissage Sciences de l'Homme et Société/Economies et finances |
|
|
| Liste des fichiers attachés à ce document : | ||||||||||
|
||||||||||
|
|
|
| hal-00362643, version 2 | |
| http://hal.archives-ouvertes.fr/hal-00362643 | |
| oai:hal.archives-ouvertes.fr:hal-00362643 | |
| Contributeur : Gilles Stoltz | |
| Soumis le : Vendredi 20 Mars 2009, 14:05:44 | |
| Dernière modification le : Vendredi 27 Mars 2009, 15:51:00 | |
