# Extreme bandits

arXiv: https://arxiv.org/abs/2604.24545 · HTML: https://mlsanity.com/paper/2604.24545/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 0 of its 23 references that are in the map.
- First posted on arXiv 27 Apr 2026.

## Built on by (most cited first, 2 of 2)

- [Theoretical Foundations of max@k Reinforcement Learning](https://mlsanity.com/paper/2607.17823/) (2026)
- [Equal-Budget Monte Carlo Tree Search versus Randomized-Restart List Scheduling for DAG Workflows: A Controlled Equal-Budget Computational Study](https://mlsanity.com/paper/2610.12542/) (2026)

## Abstract (arXiv)

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.