26447 articles – 20243 references  [version française]
Detailed view Habilitation à diriger des recherches
Université Paris-Est (14/10/2010), Alexandre Tsybakov (Pr.)
Attached file list to this document: 
PDF
hdr-hal.pdf(1.1 MB)
PS
hdr-hal.ps(1.9 MB)
PAC-Bayesian aggregation and multi-armed bandits
Jean-Yves Audibert1, 2, 3

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
3:  LIGM - Laboratoire d'Informatique Gaspard-Monge
statistical learning – aggregation problems