English

Bandits for BMO Functions

Machine Learning 2020-07-20 v1 Machine Learning

Abstract

We study the bandit problem where the underlying expected reward is a Bounded Mean Oscillation (BMO) function. BMO functions are allowed to be discontinuous and unbounded, and are useful in modeling signals with infinities in the do-main. We develop a toolset for BMO bandits, and provide an algorithm that can achieve poly-log δ\delta-regret -- a regret measured against an arm that is optimal after removing a δ\delta-sized portion of the arm space.

Keywords

Cite

@article{arxiv.2007.08703,
  title  = {Bandits for BMO Functions},
  author = {Tianyu Wang and Cynthia Rudin},
  journal= {arXiv preprint arXiv:2007.08703},
  year   = {2020}
}
R2 v1 2026-06-23T17:11:04.525Z