Informational Confidence Bounds for Self-Normalized Averages and Applications

Date: 
September, 2013
Place: 
Seville, Spain
PageStart: 
489
PageEnd: 
493
Abstract: 

We present deviation bounds for self-normalized averages and applications to estimation with a random number of observations.
The results rely on a peeling argument in exponential martingale techniques that represents an alternative to the method of mixture.
The motivating examples of bandit problems and context tree estimation are detailed.

Arxiv Number: 
1309.3376
Hal Number: 
00862062