ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 1901.08386
56
27

PAC Identification of Many Good Arms in Stochastic Multi-Armed Bandits

24 January 2019
A. Chaudhuri
Shivaram Kalyanakrishnan
ArXiv (abs)PDFHTML
Abstract

We consider the problem of identifying any kkk out of the best mmm arms in an nnn-armed stochastic multi-armed bandit. Framed in the PAC setting, this particular problem generalises both the problem of `best subset selection' and that of selecting `one out of the best m' arms [arcsk 2017]. In applications such as crowd-sourcing and drug-designing, identifying a single good solution is often not sufficient. Moreover, finding the best subset might be hard due to the presence of many indistinguishably close solutions. Our generalisation of identifying exactly kkk arms out of the best mmm, where 1≤k≤m1 \leq k \leq m1≤k≤m, serves as a more effective alternative. We present a lower bound on the worst-case sample complexity for general kkk, and a fully sequential PAC algorithm, \GLUCB, which is more sample-efficient on easy instances. Also, extending our analysis to infinite-armed bandits, we present a PAC algorithm that is independent of nnn, which identifies an arm from the best ρ\rhoρ fraction of arms using at most an additive poly-log number of samples than compared to the lower bound, thereby improving over [arcsk 2017] and [Aziz+AKA:2018]. The problem of identifying k>1k > 1k>1 distinct arms from the best ρ\rhoρ fraction is not always well-defined; for a special class of this problem, we present lower and upper bounds. Finally, through a reduction, we establish a relation between upper bounds for the `one out of the best ρ\rhoρ' problem for infinite instances and the `one out of the best mmm' problem for finite instances. We conjecture that it is more efficient to solve `small' finite instances using the latter formulation, rather than going through the former.

View on arXiv
Comments on this paper