arXiv AI By Khang Luong, Dinh Thai Son, Hoang Ta, Hung The Tran, Tuan Quang Dam

Nearly Optimal Fixed-Confidence Best-Arm Identification with 1-Bit Feedback

Read the original on arXiv AI →

The Flow has not summarised this story yet — read it at arXiv AI.

arXiv Machine Learning
Oct 8

Best Arm Identification for Bandits with Shifting Means

arXiv:2610. 10488v1 Announce Type: cross Abstract: We study the best arm identification problem in a stochastic environment with a novel form of adversarial perturbations, which we coin Shifting Means.

By Lukas Zierahn, Wouter M. Koolen, Shubhada Agrawal, Christina Katsimerou, Dirk van der Hoeven
arXiv Machine Learning
Oct 23

Bayesian Fixed-Confidence Best-Arm Identification with Abstention

The paper investigates Bayesian fixed‑confidence best‑arm identification where a learner may abstain from a final recommendation. It introduces the Screen‑and‑Confirm (S&C) algorithm, analyzes its expected stopping time, and derives lower bounds for any algorithm under error probability δ and abstention budget α constraints. For Gaussian priors, the authors provide matching upper and lower bounds, characterize exact constants for practical regimes, and show that S&C achieves optimal α–dependent rates, improving on previous results when abstention is disallowed.

By Yuqi Huang, Yunlong Hou, Vincent Y. F. Tan