arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2304.04091cs.LGcs.CYstat.ML
收藏

对子群体具有公平性约束的最优臂识别

Best Arm Identification with Fairness Constraints on Subpopulations

Department of Industrial Engineering and Operations Research, University of California, Berkeley(加州大学伯克利分校工业工程与运筹学系)

Yuhang Wu, Zeyu Zheng, Tingyu Zhu

AI总结:

本文提出并解决了BAICS问题,要求所选臂对所有子群体公平,通过证明样本复杂度下界并设计匹配阶数的算法,以高置信度识别满足约束的最优臂。

摘要:

我们提出、分析并解决了对子群体具有公平性约束的最优臂识别(BAICS)问题。标准的最优臂识别问题旨在选择一个在整体人群上期望奖励最大的臂。BAICS问题要求所选臂必须对所有子群体(如不同种族、年龄组或客户类型)公平,即满足约束:每个子群体条件下的期望奖励需大于某些阈值。BAICS问题旨在从所有满足子群体约束的臂中,以高置信度正确识别出期望奖励最大的臂。我们通过证明一个具有闭式表示的最优可达样本复杂度下界,分析了BAICS问题的复杂度。随后,我们设计了一个算法,并证明该算法的样本复杂度在阶数上与下界相匹配。最后进行了简要的数值实验以验证理论发现。

英文摘要:

We formulate, analyze and solve the problem of best arm identification with fairness constraints on subpopulations (BAICS). Standard best arm identification problems aim at selecting an arm that has the largest expected reward where the expectation is taken over the entire population. The BAICS problem requires that an selected arm must be fair to all subpopulations (e.g., different ethnic groups, age groups, or customer types) by satisfying constraints that the expected reward conditional on every subpopulation needs to be larger than some thresholds. The BAICS problem aims at correctly identify, with high confidence, the arm with the largest expected reward from all arms that satisfy subpopulation constraints. We analyze the complexity of the BAICS problem by proving a best achievable lower bound on the sample complexity with closed-form representation. We then design an algorithm and prove that the algorithm's sample complexity matches with the lower bound in terms of order. A brief account of numerical experiments are conducted to illustrate the theoretical findings.

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。

↑