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 2202.04294cs.LGcs.ITmath.ITstat.ML
收藏

具有老虎机反馈的最优聚类

Optimal Clustering with Bandit Feedback

Institute of Operations Research and Analytics(运营研究与分析研究所);National University of Singapore(新加坡国立大学);Thrust of Data Science and Analytics(数据科学与分析中心);Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Department of Mathematics(数学系);Department of Electrical and Computer Engineering(电气与计算机工程系)

Junwen Yang, Zixin Zhong, Vincent Y. F. Tan

AI总结:

针对带老虎机反馈的在线聚类问题,推导了依赖实例的信息论样本复杂度下界,提出了计算高效且渐近最优的BOC算法,其性能渐近匹配下界且优于非自适应基线。

摘要:

本文研究了带老虎机反馈的在线聚类问题。一组臂(或物品)可被划分为多个未知的组。在每个组内,与各臂相关的观测值服从具有相同均值向量的同一分布。在每个时间步,智能体查询或拉动一个臂,并从其关联的分布中获得一个独立观测值。后续的拉动动作依赖于之前的拉动操作以及此前获得的样本。智能体的任务是以最少的臂拉动次数揭示臂的潜在划分,且错误概率不超过指定常数$\delta$。该问题在病毒变异株聚类、在线市场细分等领域有诸多应用。我们给出了该任务期望样本复杂度下依赖于实例的信息论下界,并设计了一种计算高效且渐近最优的算法,即Bandit Online Clustering(BOC,老虎机在线聚类)。该算法包含一种用于自适应序贯检验的新型停止规则,无需将求解任何NP难的加权聚类问题作为其子程序。我们通过在合成数据集与真实世界数据集上的大量仿真实验表明,BOC的性能渐近匹配下界,且显著优于非自适应基线算法。

英文摘要:

This paper considers the problem of online clustering with bandit feedback. A set of arms (or items) can be partitioned into various groups that are unknown. Within each group, the observations associated to each of the arms follow the same distribution with the same mean vector. At each time step, the agent queries or pulls an arm and obtains an independent observation from the distribution it is associated to. Subsequent pulls depend on previous ones as well as the previously obtained samples. The agent's task is to uncover the underlying partition of the arms with the least number of arm pulls and with a probability of error not exceeding a prescribed constant $δ$. The problem proposed finds numerous applications from clustering of variants of viruses to online market segmentation. We present an instance-dependent information-theoretic lower bound on the expected sample complexity for this task, and design a computationally efficient and asymptotically optimal algorithm, namely Bandit Online Clustering (BOC). The algorithm includes a novel stopping rule for adaptive sequential testing that circumvents the need to exactly solve any NP-hard weighted clustering problem as its subroutines. We show through extensive simulations on synthetic and real-world datasets that BOC's performance matches the lower bound asymptotically, and significantly outperforms a non-adaptive baseline algorithm.

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。

↑