Skip to Main content Skip to Navigation
Conference papers

Informational Confidence Bounds for Self-Normalized Averages and Applications

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.
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-00862062
Contributor : Aurélien Garivier <>
Submitted on : Sunday, September 15, 2013 - 9:46:27 PM
Last modification on : Thursday, March 5, 2020 - 6:50:19 PM
Long-term archiving on: : Thursday, April 6, 2017 - 8:40:54 PM

Files

garivier.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00862062, version 1

Citation

Aurélien Garivier. Informational Confidence Bounds for Self-Normalized Averages and Applications. IEEE Information Theory Workshop, Sep 2013, Seville, Spain. pp.489-493. ⟨hal-00862062⟩

Share

Metrics

Record views

224

Files downloads

302