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.
Identifer | oai:union.ndltd.org:CCSD/oai:tel.archives-ouvertes.fr:tel-00843972 |
Date | 14 October 2010 |
Creators | Audibert, Jean-Yves |
Publisher | Université Paris-Est |
Source Sets | CCSD theses-EN-ligne, France |
Language | English |
Detected Language | English |
Type | habilitation à ¤iriger des recherches |
Page generated in 0.0118 seconds