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 , with a fixed budget of 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.
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}
}