610 articles  [version française]
Short view Habilitation à diriger des recherches
PAC-Bayesian aggregation and multi-armed bandits
Audibert J.-Y.
HDR.
[oai:tel.archives-ouvertes.fr:tel-00536084] - http://tel.archives-ouvertes.fr/tel-00536084
Attached file list to this document: 
PDF
hdr-hal.pdf(1.3 MB)
PS
hdr-hal.ps(1.9 MB)
Jean-Yves Audibert ()1, 2
1:  IMAGINE
http://imagine.enpc.fr/index.html
CSTB – Ecole des Ponts ParisTech – Université Paris-Est Créteil Val-de-Marne (UPEC)
6 avenue Blaise Pascal - Cité Descartes Champs-sur-Marne 77455 Marne-la-Vallée cedex 2
France
2:  INRIA Paris - Rocquencourt - WILLOW
INRIA – Ecole normale supérieure de Paris - ENS Paris – CNRS : UMR8548
France
PAC-Bayesian aggregation and multi-armed bandits
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.
Mathematics/Statistics
Statistics/Statistics Theory

English