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. 2305.16041
35
2
v1v2 (latest)

An ε\varepsilonε-Best-Arm Identification Algorithm for Fixed-Confidence and Beyond

25 May 2023
Marc Jourdan
Rémy Degenne
E. Kaufmann
ArXiv (abs)PDFHTML
Abstract

We propose EB-TCε\varepsilonε, a novel sampling rule for ε\varepsilonε-best arm identification in stochastic bandits. It is the first instance of Top Two algorithm analyzed for approximate best arm identification. EB-TCε\varepsilonε is an *anytime* sampling rule that can therefore be employed without modification for fixed confidence or fixed budget identification (without prior knowledge of the budget). We provide three types of theoretical guarantees for EB-TCε\varepsilonε. First, we prove bounds on its expected sample complexity in the fixed confidence setting, notably showing its asymptotic optimality in combination with an adaptive tuning of its exploration parameter. We complement these findings with upper bounds on its probability of error at any time and for any error parameter, which further yield upper bounds on its simple regret at any time. Finally, we show through numerical simulations that EB-TCε\varepsilonε performs favorably compared to existing algorithms, in different settings.

View on arXiv
Comments on this paper