Bandits for bmo functions

Conference Paper

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 domain. 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.

Duke Authors

Cited Authors

  • Wang, T; Rudin, C

Published Date

  • January 1, 2020

Published In

  • 37th International Conference on Machine Learning, Icml 2020

Volume / Issue

  • PartF168147-13 /

Start / End Page

  • 9938 - 9948

International Standard Book Number 13 (ISBN-13)

  • 9781713821120

Citation Source

  • Scopus