Precise Asymptotics and Refined Regret of Variance-Aware UCB

NeurIPSSpotlight2025

Authors
Yingying Fan, Yuxuan Han, Jinchi Lv, Xiaocong XU, Zhengyuan Zhou
Venue
NeurIPS 2025
Track
Spotlight

TL;DR

In this paper, we study the behavior of the Upper Confidence Bound-Variance (UCB-V) algorithm for the Multi-Armed Bandit (MAB) problems, a variant of the canonical Upper Confidence Bound (UCB) algorit…

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

bandit regret

Related NeurIPS papers

← All NeurIPS 2025 Spotlight papers · Browse the whole archive