English

Thresholding Bandit with Optimal Aggregate Regret

Machine Learning 2019-05-28 v1 Machine Learning

Abstract

We consider the thresholding bandit problem, whose goal is to find arms of mean rewards above a given threshold θ\theta, with a fixed budget of TT trials. We introduce LSA, a new, simple and anytime algorithm that aims to minimize the aggregate regret (or the expected number of mis-classified arms). We prove that our algorithm is instance-wise asymptotically optimal. We also provide comprehensive empirical results to demonstrate the algorithm's superior performance over existing algorithms under a variety of different scenarios.

Keywords

Cite

@article{arxiv.1905.11046,
  title  = {Thresholding Bandit with Optimal Aggregate Regret},
  author = {Chao Tao and Saùl Blanco and Jian Peng and Yuan Zhou},
  journal= {arXiv preprint arXiv:1905.11046},
  year   = {2019}
}
R2 v1 2026-06-23T09:25:48.258Z