arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2207.03091cs.LG
收藏

基于老虎机反馈的在线子模+超模(BP)最大化

Online SuBmodular + SuPermodular (BP) Maximization with Bandit Feedback

University of Washington(华盛顿大学)

Adhyyan Narang, Omid Sadeghi, Lillian J Ratliff, Maryam Fazel, Jeff Bilmes

AI总结:

本文研究在线组合目标的 BP 与弱子模最大化,提出分项反馈框架并结合 Nystrom sketching 降本,证明次线性遗憾且在推荐和子集选择中有效。

摘要:

在具有组合目标的在线交互式机器学习背景下,我们将以往纯子模的工作扩展到更一般的非子模目标。这包括:(1)那些可加性分解为两项之和的目标(一个单调子模项和一个单调超模项,称为 BP 分解);以及(2)那些仅具有弱子模性的目标。在这两种情况下,这不仅能够表示对象之间的竞争(子模)关系,还能表示互补(超模)关系,从而将该设定增强到更广泛的、能从中受益的应用(例如电影推荐、医疗治疗等)。此外,在两项情形中,我们不仅研究更常见的整体反馈方法,还研究一种新颖的框架,其中每一项都可分别获得反馈。考虑到现实世界的实用性和可扩展性,我们集成了 Nystrom sketching 技术以显著降低计算成本,包括纯子模情形。在 Gaussian process contextual bandits(高斯过程上下文老虎机)设定中,我们证明了所有情形下的次线性理论遗憾界。我们还通过实验表明其良好适用于推荐系统和数据子集选择。

英文摘要:

In the context of online interactive machine learning with combinatorial objectives, we extend purely submodular prior work to more general non-submodular objectives. This includes: (1) those that are additively decomposable into a sum of two terms (a monotone submodular and monotone supermodular term, known as a BP decomposition); and (2) those that are only weakly submodular. In both cases, this allows representing not only competitive (submodular) but also complementary (supermodular) relationships between objects, enhancing this setting to a broader range of applications (e.g., movie recommendations, medical treatments, etc.) where this is beneficial. In the two-term case, moreover, we study not only the more typical monolithic feedback approach but also a novel framework where feedback is available separately for each term. With real-world practicality and scalability in mind, we integrate Nystrom sketching techniques to significantly reduce the computational cost, including for the purely submodular case. In the Gaussian process contextual bandits setting, we show sub-linear theoretical regret bounds in all cases. We also empirically show good applicability to recommendation systems and data subset selection.

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。

↑