PAC-Bayesian aggregation and multi-armed bandits

Jean-Yves Audibert 1, 2, 3
2 WILLOW - Models of visual object recognition and scene understanding
DI-ENS - Département d'informatique de l'École normale supérieure, ENS Paris - École normale supérieure - Paris, INRIA Paris-Rocquencourt, CNRS - Centre National de la Recherche Scientifique : UMR8548
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 :
Accreditation to supervise research
Statistics [math.ST]. Université Paris-Est, 2010


https://tel.archives-ouvertes.fr/tel-00536084
Contributor : Jean-Yves Audibert <>
Submitted on : Monday, November 15, 2010 - 12:35:54 PM
Last modification on : Wednesday, October 7, 2015 - 1:16:02 AM
Document(s) archivé(s) le : Wednesday, February 16, 2011 - 2:52:56 AM

Files

hdr-hal.pdf
Files produced by the author(s)

Identifiers

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

Citation

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

Export

Share

Metrics

Record views

356

Document downloads

265