arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2311.03376cs.IRcs.LGstat.ML
收藏

分块协同老虎机:带单臂预算约束的在线协同过滤

Blocked Collaborative Bandits: Online Collaborative Filtering with Per-Item Budget Constraints

Google Research(谷歌研究院)

Soumyabrata Pal, Arun Sai Suggala, Karthikeyan Shanmugam, Prateek Jain

AI总结:

针对带单臂预算约束的分块协同老虎机问题,提出B-LATTICE算法,通过分阶段聚类与组内协同学习,在合理假设下取得首个次线性遗憾界,实验性能优于基线方法。

摘要:

我们研究分块协同老虎机问题,该问题包含多个用户,每个用户对应一个多臂老虎机问题。这些用户被划分为潜在簇,同一簇内用户的平均奖励向量完全相同。我们的目标是设计算法,在每个用户的任意臂被拉动次数不超过B次的约束下,最大化所有用户随时间累积的总奖励。该问题最初由文献[Bresler:2014]提出,此后为其设计遗憾最优算法一直是一个公开难题。在本研究中,我们提出了一种名为B-LATTICE(基于矩阵补全的分块潜在老虎机)的算法,该算法在满足预算约束的同时实现跨用户协同,以最大化累积奖励。理论上,在关于潜在结构的若干合理假设下,当存在M个用户、N个臂、每个用户经历T轮,且潜在簇数量C=O(1)时,在预算约束B=Θ(log T)的条件下,B-LATTICE的单用户遗憾为$\tilde{O}(\frac{T}{1 + N M^{-1}})$。这是该问题的首个次线性遗憾界,且当B=T时与极小极大遗憾界相匹配。实验结果表明,即使在B=1的情况下,我们的算法性能也优于基线方法。B-LATTICE采用分阶段运行的方式,每个阶段先将用户聚类为不同组,再通过组内用户间的协同快速学习其奖励模型。

英文摘要:

We consider the problem of \emph{blocked} collaborative bandits where there are multiple users, each with an associated multi-armed bandit problem. These users are grouped into \emph{latent} clusters such that the mean reward vectors of users within the same cluster are identical. Our goal is to design algorithms that maximize the cumulative reward accrued by all the users over time, under the \emph{constraint} that no arm of a user is pulled more than $\mathsf{B}$ times. This problem has been originally considered by \cite{Bresler:2014}, and designing regret-optimal algorithms for it has since remained an open problem. In this work, we propose an algorithm called \texttt{B-LATTICE} (Blocked Latent bAndiTs via maTrIx ComplEtion) that collaborates across users, while simultaneously satisfying the budget constraints, to maximize their cumulative rewards. Theoretically, under certain reasonable assumptions on the latent structure, with $\mathsf{M}$ users, $\mathsf{N}$ arms, $\mathsf{T}$ rounds per user, and $\mathsf{C}=O(1)$ latent clusters, \texttt{B-LATTICE} achieves a per-user regret of $\widetilde{O}(\sqrt{\mathsf{T}(1 + \mathsf{N}\mathsf{M}^{-1})}$ under a budget constraint of $\mathsf{B}=Θ(\log \mathsf{T})$. These are the first sub-linear regret bounds for this problem, and match the minimax regret bounds when $\mathsf{B}=\mathsf{T}$. Empirically, we demonstrate that our algorithm has superior performance over baselines even when $\mathsf{B}=1$. \texttt{B-LATTICE} runs in phases where in each phase it clusters users into groups and collaborates across users within a group to quickly learn their reward models.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑