English

Optimal Thresholding Linear Bandit

Machine Learning 2024-02-16 v1 Machine Learning

Abstract

We study a novel pure exploration problem: the ϵ\epsilon-Thresholding Bandit Problem (TBP) with fixed confidence in stochastic linear bandits. We prove a lower bound for the sample complexity and extend an algorithm designed for Best Arm Identification in the linear case to TBP that is asymptotically optimal.

Keywords

Cite

@article{arxiv.2402.09467,
  title  = {Optimal Thresholding Linear Bandit},
  author = {Eduardo Ochoa Rivera and Ambuj Tewari},
  journal= {arXiv preprint arXiv:2402.09467},
  year   = {2024}
}

Comments

arXiv admin note: substantial text overlap with arXiv:2006.16073 by other authors

R2 v1 2026-06-28T14:48:51.418Z