Work

Informational confidence bounds for self-normalized averages and applications

Year: 2013

Type: conference-paper

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.

Source: IEEE Information Theory Workshop (ITW)

DOI: 10.1109/itw.2013.6691311

Author: Aurelien Garivier

Institutions: Université Toulouse III - Paul Sabatier, Université de Toulouse, Institut de Mathématiques de Toulouse

Language: English

Topic: Advanced Bandit Algorithms Research

Subfield: Management Science and Operations Research

Field: Decision Sciences

Domain: Social Sciences

Open Access status: green

OpenAlex ID: W2014801173

FWCI: 5.072

Cites: 31

Cited by: 74

Related to: 10