arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.05575cs.LGcs.AIcs.CYcs.MA
收藏

在随机多臂老虎机中同时实现组曝光公平性与组内精英治理

Simultaneously Achieving Group Exposure Fairness and Within-Group Meritocracy in Stochastic Bandits

Indian Institute of Technology Ropar(印度理工学院罗帕尔分校);Indian Institute of Technology Hyderabad(印度理工学院海得拉巴分校);International Institute of Information Technology, Hyderabad(国际信息技术学院海得拉巴分校)

Subham Pokhriyal, Shweta Jain, Ganesh Ghalme, Swapnil Dhamal, Sujit Gujar

AI总结:

针对随机多臂老虎机中的分组公平性问题,提出双层公平性概念,并设计BF-UCB算法同时保证组曝光公平与组内精英治理,实现次线性遗憾且不显著损失奖励。

摘要:

现有的随机多臂老虎机(MAB)公平性方法主要关注对个体臂的曝光保证。当臂按某些属性自然分组时,我们提出了双层公平性(Bi-Level Fairness),该概念考虑两个层面的公平性。在第一层,双层公平性保证每个组获得一定的最低曝光量。为了解决组内个体臂拉取分配不均的问题,我们在第二层考虑精英治理公平性,确保每个臂根据其在组内的功绩被拉取。我们的工作表明,我们可以调整基于UCB的算法来实现双层公平性,通过提供(i)随时(anytime)组曝光公平性保证和(ii)确保每个组内的个体层面精英治理公平性。我们首先表明可以将遗憾界分解为两个部分:(a)由于随时组曝光公平性产生的遗憾和(b)由于每个组内精英治理公平性产生的遗憾。我们提出的算法BF-UCB最优地平衡这两种遗憾,以达到遗憾的上界$O(\sqrt{T})$,其中$T$为停止时间。借助模拟实验,我们进一步表明BF-UCB实现了次线性遗憾;与现有算法相比,提供了更好的组和个体曝光保证;并且相对于不施加任何公平性约束的UCB算法,在奖励方面没有显著下降。

英文摘要:

Existing approaches to fairness in stochastic multi-armed bandits (MAB) primarily focus on exposure guarantee to individual arms. When arms are naturally grouped by certain attribute(s), we propose Bi-Level Fairness, which considers two levels of fairness. At the first level, Bi-Level Fairness guarantees a certain minimum exposure to each group. To address the unbalanced allocation of pulls to individual arms within a group, we consider meritocratic fairness at the second level, which ensures that each arm is pulled according to its merit within the group. Our work shows that we can adapt a UCB-based algorithm to achieve a Bi-Level Fairness by providing (i) anytime Group Exposure Fairness guarantees and (ii) ensuring individual-level Meritocratic Fairness within each group. We first show that one can decompose regret bounds into two components: (a) regret due to anytime group exposure fairness and (b) regret due to meritocratic fairness within each group. Our proposed algorithm BF-UCB balances these two regrets optimally to achieve the upper bound of $O(\sqrt{T})$ on regret; $T$ being the stopping time. With the help of simulated experiments, we further show that BF-UCB achieves sub-linear regret; provides better group and individual exposure guarantees compared to existing algorithms; and does not result in a significant drop in reward with respect to UCB algorithm, which does not impose any fairness constraint.

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。

↑