arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.20489cs.LG
收藏

预算约束下的在线决策延迟

Online Decision Deferral under Budget Constraints

Georgia Institute of Technology(佐治亚理工学院);Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所);University of Tübingen(蒂宾根大学)

Mirabel Reid, Tom Sühr, Claire Vernade, Samira Samadi

AI总结:

本文针对预算约束下模型与专家决策延迟的在线自适应问题,提出上下文赌博机框架及其高效扩展,在真实数据集上验证了显著性能。

摘要:

机器学习(ML)模型越来越多地被用于支持或替代决策。在熟练专家是有限资源的应用中,当ML模型的性能至少与专家质量相当时,减少专家负担并自动化决策至关重要。然而,模型通常是预先训练且固定的,而任务按顺序到达,其分布可能发生偏移。在这种情况下,决策者各自的表现可能发生变化,延迟算法必须保持自适应性。我们提出了该在线决策问题的上下文赌博机模型。我们的框架包含预算约束和不同类型的部分反馈模型。除了算法的理论保证外,我们还提出了高效的扩展方法,在真实世界数据集上取得了显著的性能。

英文摘要:

Machine Learning (ML) models are increasingly used to support or substitute decision making. In applications where skilled experts are a limited resource, it is crucial to reduce their burden and automate decisions when the performance of an ML model is at least of equal quality. However, models are often pre-trained and fixed, while tasks arrive sequentially and their distribution may shift. In that case, the respective performance of the decision makers may change, and the deferral algorithm must remain adaptive. We propose a contextual bandit model of this online decision making problem. Our framework includes budget constraints and different types of partial feedback models. Beyond the theoretical guarantees of our algorithm, we propose efficient extensions that achieve remarkable performance on real-world datasets.

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。

↑