PAC-Bayesian aggregation and multi-armed bandits

Jean-Yves Audibert 1, 2, 3
1 IMAGINE [Marne-la-Vallée]
LIGM - Laboratoire d'Informatique Gaspard-Monge, CSTB - Centre Scientifique et Technique du Bâtiment, ENPC - École des Ponts ParisTech
2 WILLOW - Models of visual object recognition and scene understanding
CNRS - Centre National de la Recherche Scientifique : UMR8548, Inria Paris-Rocquencourt, DI-ENS - Département d'informatique de l'École normale supérieure
Abstract : 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.
Document type :
Habilitation à diriger des recherches
Complete list of metadatas

Cited literature [130 references]  Display  Hide  Download
Contributor : Jean-Yves Audibert <>
Submitted on : Monday, November 15, 2010 - 12:35:54 PM
Last modification on : Wednesday, January 30, 2019 - 11:07:51 AM
Long-term archiving on : Wednesday, February 16, 2011 - 2:52:56 AM


Files produced by the author(s)


  • HAL Id : tel-00536084, version 1
  • ARXIV : 1011.3396


Jean-Yves Audibert. PAC-Bayesian aggregation and multi-armed bandits. Statistics [math.ST]. Université Paris-Est, 2010. ⟨tel-00536084⟩



Record views


Files downloads