Extreme bandits - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2014

Extreme bandits

Alexandra Carpentier
  • Function : Author
  • PersonId : 961172
Michal Valko

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.
Fichier principal
Vignette du fichier
carpentier2014extreme.pdf (361.84 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01079354 , version 1 (01-11-2014)
hal-01079354 , version 2 (03-11-2014)

Identifiers

  • HAL Id : hal-01079354 , version 2

Cite

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

Share

Gmail Facebook X LinkedIn More