Skip to Main content Skip to Navigation
Conference papers

Extreme bandits

Alexandra Carpentier 1 Michal Valko 2
1 Statistical Laboratory [Cambridge]
DPMMS - Department of Pure Mathematics and Mathematical Statistics
2 SEQUEL - Sequential Learning
LIFL - Laboratoire d'Informatique Fondamentale de Lille, Inria Lille - Nord Europe, LAGIS - Laboratoire d'Automatique, Génie Informatique et Signal
Abstract : In many areas of medicine, security, and life sciences, we want to allocate limited resources to different sources in order to detect extreme values. In this paper, we study an efficient way to allocate these resources sequentially under limited feedback. While sequential design of experiments is well studied in bandit theory, the most commonly optimized property is the regret with respect to the maximum mean reward. However, in other problems such as network intrusion detection, we are interested in detecting the most extreme value output by the sources. Therefore, in our work we study extreme regret which measures the efficiency of an algorithm compared to the oracle policy selecting the source with the heaviest tail. We propose the ExtremeHunter algorithm, provide its analysis, and evaluate it empirically on synthetic and real-world experiments.
Document type :
Conference papers
Complete list of metadata

Cited literature [22 references]  Display  Hide  Download
Contributor : Michal Valko Connect in order to contact the contributor
Submitted on : Monday, November 3, 2014 - 9:58:26 AM
Last modification on : Thursday, January 20, 2022 - 4:17:14 PM


Files produced by the author(s)


  • HAL Id : hal-01079354, version 2


Alexandra Carpentier, Michal Valko. Extreme bandits. Neural Information Processing Systems, Dec 2014, Montréal, Canada. ⟨hal-01079354v2⟩



Les métriques sont temporairement indisponibles