arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.12094cs.LG
收藏

带瓶颈报酬函数的组合纯探索

Combinatorial Pure Exploration with Bottleneck Reward Function

Tsinghua University(清华大学);The University of Tokyo(东京大学);RIKEN(日本理化学研究所);Microsoft Research(微软研究院)

Yihan Du, Yuko Kuroki, Wei Chen

摘要:

本文研究了在固定置信度和固定预算条件下具有瓶颈报酬函数的组合纯探索问题。在CPE-B中,给定一组基臂和基臂子集的集合,(超级手臂)遵循一定的组合约束,学习者顺序地玩基本手臂并观察其随机奖励,目的是找到具有最大瓶颈值的最佳超级手臂,定义为超级武器中包含的基本武器的最低预期奖励。CPE-B模型涵盖了通信网络中的网络路由等多种实际场景,其\emph{unique challenges}的关键在于如何利用瓶颈特性节省样本,达到统计最优。现有的CPE研究(其中大多数假设线性奖励)都不能适应解决这些挑战,因此我们开发了全新的技术来处理它们。对于FC设置,我们提出了新的算法,最佳的样本复杂度为一个广泛的家庭的情况下,并建立一个匹配的下限,以证明最优性(对数因子内)。对于FB设置,我们设计了一种算法,实现了最先进的错误概率保证,是第一个有效地运行在固定预算的路径实例,相比现有的CPE算法。我们的实验结果的顶部- $k$,路径和匹配的情况下验证了经验的优越性,所提出的算法在其基线。

英文摘要:

In this paper, we study the Combinatorial Pure Exploration problem with the Bottleneck reward function (CPE-B) under the fixed-confidence (FC) and fixed-budget (FB) settings. In CPE-B, given a set of base arms and a collection of subsets of base arms (super arms) following a certain combinatorial constraint, a learner sequentially plays a base arm and observes its random reward, with the objective of finding the optimal super arm with the maximum bottleneck value, defined as the minimum expected reward of the base arms contained in the super arm. CPE-B captures a variety of practical scenarios such as network routing in communication networks, and its \emph{unique challenges} fall on how to utilize the bottleneck property to save samples and achieve the statistical optimality. None of the existing CPE studies (most of them assume linear rewards) can be adapted to solve such challenges, and thus we develop brand-new techniques to handle them. For the FC setting, we propose novel algorithms with optimal sample complexity for a broad family of instances and establish a matching lower bound to demonstrate the optimality (within a logarithmic factor). For the FB setting, we design an algorithm which achieves the state-of-the-art error probability guarantee and is the first to run efficiently on fixed-budget path instances, compared to existing CPE algorithms. Our experimental results on the top-$k$, path and matching instances validate the empirical superiority of the proposed algorithms over their baselines.

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。

↑