English

Multiarmed Bandits With Limited Expert Advice

Machine Learning 2013-07-09 v4

Abstract

We solve the COLT 2013 open problem of \citet{SCB} on minimizing regret in the setting of advice-efficient multiarmed bandits with expert advice. We give an algorithm for the setting of K arms and N experts out of which we are allowed to query and use only M experts' advices in each round, which has a regret bound of \tilde{O}\bigP{\sqrt{\frac{\min\{K, M\} N}{M} T}} after T rounds. We also prove that any algorithm for this problem must have expected regret at least \tilde{\Omega}\bigP{\sqrt{\frac{\min\{K, M\} N}{M}T}}, thus showing that our upper bound is nearly tight.

Keywords

Cite

@article{arxiv.1306.4653,
  title  = {Multiarmed Bandits With Limited Expert Advice},
  author = {Satyen Kale},
  journal= {arXiv preprint arXiv:1306.4653},
  year   = {2013}
}

Comments

Updated with tighter upper bound based on PolyINF algorithm, lower bound nearly matching the upper bound, and fixed some typos

R2 v1 2026-06-22T00:37:03.404Z