arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2401.03756cs.LGcs.AIecon.EMstat.MEstat.ML
收藏

策略学习的自适应实验设计

Adaptive Experimental Design for Policy Learning

Data Analytics Team, Mizuho–DL Financial Technology, Co., Ltd.(摩根大通数字金融技术公司数据分析团队);Department of Economics, Northwestern University(西北大学经济学系);Graduate School of Economics and Management, Tohoku University(东北大学经济学与管理学院);Department of Economics, Brown University(布朗大学经济学系)

Masahiro Kato, Kyohei Okumura, Takuya Ishihara, Toru Kitagawa

AI总结:

本研究针对情境最佳臂识别问题,提出自适应采样-策略学习(PLAS)策略,以根据情境信息识别最佳治疗臂,并证明其在最坏情况期望遗憾下达到极小极大最优速率。

摘要:

本研究探讨了情境最佳臂识别(BAI)问题,旨在设计一个自适应实验,以根据情境信息(协变量)识别最佳治疗臂。我们考虑一个决策者,在实验期间将治疗臂分配给实验单元,并在实验结束时根据情境推荐估计的最佳治疗臂。决策者使用一个策略进行推荐,该策略是一个根据情境提供估计最佳治疗臂的函数。在我们的评估中,我们关注最坏情况下的期望遗憾,这是最优策略的期望结果与我们所提策略的期望结果之间的相对度量。我们推导了期望简单遗憾的下界,然后提出了一种称为自适应采样-策略学习(PLAS)的策略。我们证明该策略在极小极大速率上是最优的,即随着实验单元数量的增加,其遗憾上界中的主导因子与下界相匹配。

英文摘要:

This study investigates the contextual best arm identification (BAI) problem, aiming to design an adaptive experiment to identify the best treatment arm conditioned on contextual information (covariates). We consider a decision-maker who assigns treatment arms to experimental units during an experiment and recommends the estimated best treatment arm based on the contexts at the end of the experiment. The decision-maker uses a policy for recommendations, which is a function that provides the estimated best treatment arm given the contexts. In our evaluation, we focus on the worst-case expected regret, a relative measure between the expected outcomes of an optimal policy and our proposed policy. We derive a lower bound for the expected simple regret and then propose a strategy called Adaptive Sampling-Policy Learning (PLAS). We prove that this strategy is minimax rate-optimal in the sense that its leading factor in the regret upper bound matches the lower bound as the number of experimental units increases.

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。

↑