arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1901.09427cs.GT
收藏

战略代理人之间不可分割产品的公平分配

Fair Division of Indivisible Goods Among Strategic Agents

Siddharth Barman, Ganesh Ghalme, Shweta Jain, Pooja Kulkarni, Shivika Narang

摘要:

本文研究了单参数环境下不可分割商品的公平分割问题。特别是,我们开发了真正的社会福利最大化机制,公平分配不可分割的商品。我们的公平保证是在解决方案概念方面,这些概念是为解决不可分割的货物分配而量身定制的,因此,为公平分配货物提供了适当的框架。这项工作特别考虑公平的嫉妒自由度高达一个好(EF 1),最大最小份额保证(MMS)和纳什社会福利(新南威尔士州)。我们的第一个结果表明,(在一个单参数的环境)的福利最大化的问题,受约束的不可分割的商品的分配是EF 1,承认一个多项式时间,1/2近似,真实的拍卖。我们进一步证明了这个问题是NP-困难的,因此,近似是有道理的。这个硬度的结果也补充了以前的作品,表明可以有效地计算任意的EF 1分配。对于MMS约束下的社会福利最大化问题,我们还建立了一个双准则近似保证。特别是,我们开发了一个真实的拍卖,有效地找到一个分配,其中每个代理人得到一个捆绑的价值至少$\left(1/2 - \varepsilon \right)$倍,她的maximin份额和福利的计算分配至少是最佳的,这里$\varepsilon >0$是一个固定的常数。我们补充这一结果表明,福利最大化是计算困难的,即使一个目标是只满足MMS约束近似。

英文摘要:

We study fair division of indivisible goods in a single-parameter environment. In particular, we develop truthful social welfare maximizing mechanisms for fairly allocating indivisible goods. Our fairness guarantees are in terms of solution concepts which are tailored to address allocation of indivisible goods and, hence, provide an appropriate framework for fair division of goods. This work specifically considers fairness in terms of envy freeness up to one good (EF1), maximin share guarantee (MMS), and Nash social welfare (NSW). Our first result shows that (in a single-parameter environment) the problem of maximizing welfare, subject to the constraint that the allocation of the indivisible goods is EF1, admits a polynomial-time, 1/2-approximate, truthful auction. We further prove that this problem is NP-Hard and, hence, an approximation is warranted. This hardness result also complements prior works which show that an arbitrary EF1 allocation can be computed efficiently. We also establish a bi-criteria approximation guarantee for the problem of maximizing social welfare under MMS constraints. In particular, we develop a truthful auction which efficiently finds an allocation wherein each agent gets a bundle of value at least $\left(1/2 - \varepsilon \right)$ times her maximin share and the welfare of the computed allocation is at least the optimal, here $\varepsilon >0$ is a fixed constant. We complement this result by showing that maximizing welfare is computationally hard even if one aims to only satisfy the MMS constraint approximately.

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。

↑