arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.11437cs.GTecon.TH
收藏

分配博弈的公平核心分配:新的解概念和高效算法

Fair Core Imputations for the Assignment Game: New Solution Concepts and Efficient Algorithms

University of California, Irvine(加州大学尔湾分校)

Vijay V. Vazirani

AI总结:

本文提出三种新的个体公平性解概念,并为每个概念设计高效算法,以解决分配博弈中个体层面的公平性问题。

摘要:

分配博弈是利润分配的经典模型,也是合作博弈理论的基石。虽然其核心分配在联盟层面保证了公平性,但对个体层面却没有公平保证:单个个体或单边联盟的独立价值为零,可能获得任意小的报酬。受对个体层面公平性日益增长的关注启发,我们提出问题:能否选择一个核心分配,同时对个体公平?我们引入了三种以个体公平性为导向的解概念,每种都以不同的方式促进公平。Leximin和Leximax核心分配扩展了最大最小和最小最大公平性,分别提升最不利者的利益并约束最有利者的利益。Min spread核心分配最小化最大和最小正报酬之间的差距,促进公平的利润分配。对于所有三种解概念,我们开发了组合型、强多项式算法。Leximin和Leximax算法基于一种新的对偶理论适应方法,而Min spread算法结合了前两种算法的部分执行。我们期待这项工作能重新激发对强大对偶理论的创新,并促进进一步的公平性和稳定性算法研究。

英文摘要:

The assignment game is a classical model for profit sharing and a cornerstone of cooperative game theory. While an imputation in its core guarantees fairness among coalitions, it provides no fairness guarantee at the level of individual agents: single agents or one sided coalitions have zero standalone value and may receive arbitrarily small payoffs. Motivated by the growing focus on individual level fairness, we ask: Can one select a core imputation that is also fair to individuals? We introduce three individual fairness driven solution concepts, each promoting equity in a different way. The leximin and leximax core imputations extend max min and min max fairness to uplift the least advantaged and constrain the most advantaged agents, respectively. The min spread core imputation minimizes the gap between the largest and smallest positive payoffs, promoting equitable profit distribution. For all three solution concepts, we develop combinatorial, strongly polynomial algorithms. The leximin and leximax algorithms are based on a novel adaptation of the primal dual paradigm, while the min spread algorithm combines partial executions of the first two. We expect our work to revive innovation on the potent primal dual paradigm as well as promote further work on the algorithmic study of fairness and stability.

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。

↑