Extreme bandits

Carpentier, Alexandra; Valko, Michal

Document type :

Communication dans un congrès avec actes

Title :

Extreme bandits

Author(s) :

Carpentier, Alexandra [Auteur]
Statistical Laboratory [Cambridge]
Valko, Michal [Auteur]

Sequential Learning [SEQUEL]

Conference title :

Neural Information Processing Systems

City :

Montréal

Country :

Canada

Start date of the conference :

2014-12-07

HAL domain(s) :

Statistiques [stat]/Machine Learning [stat.ML]

English abstract : [en]

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 ...
Show more >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.Show less >

Language :

Anglais

Peer reviewed article :

Oui

Audience :

Internationale

Popular science :

Non

Collections :