Bayesian Fixed-Confidence Best-Arm Identification with Abstention
We study the Bayesian fixed-confidence best-arm identification problem in which a learner can abstain from making a terminal recommendation. Subject to a target error probability $\delta$ and an abstention budget $\alpha$, we propose Screen-and-Confirm (S&C) and analyze its expected stopping time.
By Yuqi Huang, Yunlong Hou, Vincent Y. F. TanarXiv cs.LG
Read the full story
Originally published by arXiv cs.LG on Oct 23, 2026.
Comments
Sign in to join the discussion.