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 -regret -- a regret measured against an arm that is optimal after removing a -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}
}