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 2301.12571cs.LGcs.CYcs.IRecon.GNq-fin.EC
收藏

基于合成控制预言机的有界(O(1))遗憾推荐学习

Bounded (O(1)) Regret Recommendation Learning via Synthetic Controls Oracle

University of Washington(华盛顿大学);Texas A&M University(得克萨斯农工大学)

Enoch Hyunwook Kang, P. R. Kumar

AI总结:

针对实际推荐系统中线性模型假设难以满足及多种现实问题,本文提出基于合成控制方法(SCM)作为实用放松假设,在理论上实现了有界遗憾推荐学习,并通过模拟实验验证。

摘要:

在具有固定偏好的用户重复到达的在线探索系统中,最近研究表明,当系统被建模为线性上下文bandit时,可以实现O(1)即有界遗憾。这一结果对推荐系统可能很有意义,因为其物品流行度通常短暂,探索本身可以在潜在的长期非平稳性发挥作用之前快速完成。然而在实践中,精确了解线性模型难以证明。此外,不可观测协变量的潜在存在、不均匀的用户到达率、必要秩条件的解释以及用户选择退出私人数据跟踪等问题,都需要在实际推荐系统应用中加以解决。在这项工作中,我们进行理论研究以解决所有这些问题,同时仍实现有界遗憾。除了证明技巧外,我们在此做出的关键区分假设是存在有效的合成控制方法(SCM),这被证明是对精确线性模型知识假设的实用放松。我们使用最小模拟实验验证了理论有界遗憾结果。

英文摘要:

In online exploration systems where users with fixed preferences repeatedly arrive, it has recently been shown that O(1), i.e., bounded regret, can be achieved when the system is modeled as a linear contextual bandit. This result may be of interest for recommender systems, where the popularity of their items is often short-lived, as the exploration itself may be completed quickly before potential long-run non-stationarities come into play. However, in practice, exact knowledge of the linear model is difficult to justify. Furthermore, potential existence of unobservable covariates, uneven user arrival rates, interpretation of the necessary rank condition, and users opting out of private data tracking all need to be addressed for practical recommender system applications. In this work, we conduct a theoretical study to address all these issues while still achieving bounded regret. Aside from proof techniques, the key differentiating assumption we make here is the presence of effective Synthetic Control Methods (SCM), which are shown to be a practical relaxation of the exact linear model knowledge assumption. We verify our theoretical bounded regret result using a minimal simulation experiment.

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。

↑