 |
|
|
|
| Fiche détaillée | HDR |
|
|
|
|
| Liste des fichiers attachés à ce document : | ||||||||||
|
||||||||||
|
|
|
| PAC-Bayesian aggregation and multi-armed bandits |
|
|
| Jean-Yves Audibert1, 2 |
|
|
|
| This habilitation thesis presents several contributions to (1) the PAC-Bayesian analysis of statistical learning, (2) the three aggregation problems: given d functions, how to predict as well as (i) the best of these d functions (model selection type aggregation), (ii) the best convex combination of these d functions, (iii) the best linear combination of these d functions, (3) the multi-armed bandit problems. |
|
|
|
|
|
|
|
|
|
| 1 : | IMAGINE |
|
|
| 2 : | INRIA Paris - Rocquencourt - WILLOW |
|
|
|
|
|
|
|
| tel-00536084, version 1 | |
| http://tel.archives-ouvertes.fr/tel-00536084 | |
| oai:tel.archives-ouvertes.fr:tel-00536084 | |
| Contributeur : Jean-Yves Audibert | |
| Soumis le : Lundi 15 Novembre 2010, 12:35:54 | |
| Dernière modification le : Lundi 15 Novembre 2010, 15:19:24 | |
