arXiv:2605. 02141v2 Announce Type: replace-cross Abstract: Kullback-Leibler (KL) regularization is widely used in offline decision-making and offers several benefits, motivating recent work on the sample complexity of offline learning with respect to KL-regularized performance metrics.
By Kaixuan Ji, Qiwei Di, Heyang Zhao, Qingyue Zhao, Quanquan Gu
The paper investigates multi‑armed bandits where several arms are optimal. It refines previous sub‑sampling algorithms to achieve a minimax regret of τO((K−A)/√(KA)·√T), improving on earlier bounds. A matching lower bound is provided, showing the rate is nearly optimal, and the authors demonstrate that knowing the number of optimal arms A (within constant factors) is essential for near‑optimal performance.
By Kaixuan Ji, Qiwei Di, Qingyue Zhao, Heyang Zhao, Quanquan Gu
arXiv:2609. 38659v1 Announce Type: cross Abstract: We study multi-armed bandits (MAB) with multiple optimal arms, motivated by the fact that many practical decision making problems admit multiple correct answers.
By Kaixuan Ji, Qiwei Di, Qingyue Zhao, Heyang Zhao, Quanquan Gu
arXiv:2606. 27448v1 Announce Type: new Abstract: This paper studies the problem of regret minimization in Markovian bandits with \emph{non-observable states} and possibly \emph{constrained} decision epochs.
By Thomas Hira, Victor Boone, Urtzi Ayesta, Ina Maria Verloop
arXiv:2602. 23116v3 Announce Type: replace Abstract: We consider the problem of regularized best-response max-regret minimization in online RLHF under general preferences and bandit feedback.
By Junghyun Lee, Minju Hong, Kwang-Sung Jun, Chulhee Yun, Se-Young Yun
arXiv:2510. 22819v3 Announce Type: replace Abstract: The convergence analysis of online learning algorithms is central to machine learning theory, where the last-iterate convergence is particularly important, as it captures the learner's actual decisions and describes the evolution of the learning process over time.
By Jingxin Zhan, Yuze Han, Zhihua Zhang