Work

Extreme bandits

Year: 2026

Type: preprint

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.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2604.24545

Authors: Carpentier, Alexandra, Valko, Michal

Institutions: University of Cambridge, Institut national de recherche en sciences et technologies du numérique, Sequella (United States), Centre Inria de l'Université de Lille

Topic: Advanced Bandit Algorithms Research

Subfield: Management Science and Operations Research

Field: Decision Sciences

Domain: Social Sciences

Open Access status: green

OpenAlex ID: W7156644515

Cites:

Cited by:

Related to: