PAC-Bayesian aggregation and multi-armed bandits
Statistics Theory
2010-11-17 v1 Statistics Theory
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.
Cite
@article{arxiv.1011.3396,
title = {PAC-Bayesian aggregation and multi-armed bandits},
author = {Jean-Yves Audibert},
journal= {arXiv preprint arXiv:1011.3396},
year = {2010}
}