arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.15788stat.MLcs.LG
收藏

用于多维在线决策的随机低秩张量老虎机

Stochastic Low-rank Tensor Bandits for Multi-dimensional Online Decision Making

Amazon(亚马逊);Deepmind(深度思维);Miami Herbert Business School, University of Miami(迈阿密大学迈阿密赫伯特商学院);Krannert School of Management, Purdue University(普渡大学克兰纳特管理学院)

Jie Zhou, Botao Hao, Zheng Wen, Jingfei Zhang, Will Wei Sun

AI总结:

本文提出了随机低秩张量老虎机,用于解决多维在线决策问题,通过张量消元、张量周期贪婪和张量集成采样算法,在理论和实验中均优于忽略低秩结构的现有方法。

摘要:

多维在线决策在许多实际应用中发挥着至关重要的作用,如在线推荐和数字营销。在这些问题的每一个时刻,决策是来自不同类型实体的选择的组合。为了解决这个问题,我们引入了随机低秩张量老虎机,这是一类均值奖励可以表示为低秩张量的老虎机。我们考虑了两种设置:无上下文的张量老虎机和有上下文的张量老虎机。在第一种设置中,平台旨在寻找具有最高期望奖励的最优决策,即真实奖励张量的最大条目。在第二种设置中,张量的某些模式是上下文,其余模式是决策,目标是在给定上下文信息的情况下找到最优决策。我们提出了两种学习算法——用于无上下文张量老虎机的张量消元和张量周期贪婪,并为它们推导出了有限时间遗憾界限。与现有的竞争方法相比,张量消元具有最佳的总体遗憾界限,而张量周期贪婪对奖励张量的维度具有更敏锐的依赖性。此外,我们开发了一种实用且有效的贝叶斯算法,称为张量集成采样,用于有上下文的张量老虎机。在在线广告数据上的广泛模拟和实际分析支持了我们的理论发现,并表明我们的算法优于各种忽略张量低秩结构的最先进方法。

英文摘要:

Multi-dimensional online decision making plays a crucial role in many real applications such as online recommendation and digital marketing. In these problems, a decision at each time is a combination of choices from different types of entities. To solve it, we introduce stochastic low-rank tensor bandits, a class of bandits whose mean rewards can be represented as a low-rank tensor. We consider two settings, tensor bandits without context and tensor bandits with context. In the first setting, the platform aims to find the optimal decision with the highest expected reward, a.k.a, the largest entry of true reward tensor. In the second setting, some modes of the tensor are contexts and the rest modes are decisions, and the goal is to find the optimal decision given the contextual information. We propose two learning algorithms tensor elimination and tensor epoch-greedy for tensor bandits without context, and derive finite-time regret bounds for them. Comparing with existing competitive methods, tensor elimination has the best overall regret bound and tensor epoch-greedy has a sharper dependency on dimensions of the reward tensor. Furthermore, we develop a practically effective Bayesian algorithm called tensor ensemble sampling for tensor bandits with context. Extensive simulations and real analysis in online advertising data back up our theoretical findings and show that our algorithms outperform various state-of-the-art approaches that ignore the tensor low-rank structure.

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。

↑