动态公平分配中的一致有界遗憾
Uniformly Bounded Regret in Dynamic Fair Allocation
AI总结:
针对动态公平分配问题,提出BIRT策略,通过有限次重解确定性替代问题,在Hölder均值福利度量下实现一致有界遗憾,兼顾效率与公平。
摘要:
我们研究一个动态分配问题,其中$T$个依次到达的可分割资源被分配给若干具有线性效用的智能体。每个资源对智能体的边际效用从已知的联合分布中随机抽取,随时间独立同分布,中央规划者需立即做出不可撤销的分配决策。大多数关于动态资源分配的工作旨在最大化功利主义福利,即分配的效率,这可能导致资源不公平地集中在某些高效用智能体上,而其他智能体的需求得不到满足。在本文中,为了平衡效率和公平性,我们转而考虑广泛的福利度量族——Hölder均值,其中包括纳什社会福利和平等主义福利。为此,我们首先研究一种基于流体的策略,该策略源自底层问题的确定性替代模型,并证明对于所有光滑的Hölder均值福利度量,相对于事后最优(即在分配决策前已知所有效用时的最优福利),该策略在时间范围长度$T$上达到$O(1)$的遗憾。然而,当在非光滑的平等主义福利下评估时,基于流体的策略达到的遗憾阶为$\Theta(\sqrt{T})$。然后,我们在此基础上提出一种新策略,称为带阈值的后向不频繁重解($\mathsf{BIRT}$),该策略最多重解确定性替代问题$O(\log\log T)$次。我们证明$\mathsf{BIRT}$策略相对于事后最优平等主义福利达到$O(1)$的遗憾,与时间范围长度$T$无关。最后,我们通过数值实验来验证我们的理论主张,并说明相对于几种基准策略的显著性能改进。
英文摘要:
We study a dynamic allocation problem in which $T$ sequentially arriving divisible resources are to be allocated to a number of agents with linear utilities. The marginal utilities of each resource to the agents are drawn stochastically from a known joint distribution, independently and identically across time, and the central planner makes immediate and irrevocable allocation decisions. Most works on dynamic resource allocation aim to maximize the utilitarian welfare, i.e., the efficiency of the allocation, which may result in unfair concentration of resources on certain high-utility agents while leaving others' demands under-fulfilled. In this paper, aiming at balancing efficiency and fairness, we instead consider a broad collection of welfare metrics, the Hölder means, which includes the Nash social welfare and the egalitarian welfare. To this end, we first study a fluid-based policy derived from a deterministic surrogate to the underlying problem and show that for all smooth Hölder mean welfare metrics it attains an $O(1)$ regret over the time horizon length $T$ against the hindsight optimum, i.e., the optimal welfare if all utilities were known in advance of deciding on allocations. However, when evaluated under the non-smooth egalitarian welfare, the fluid-based policy attains a regret of order $Θ(\sqrt{T})$. We then propose a new policy built thereupon, called Backward Infrequent Re-solving with Thresholding ($\mathsf{BIRT}$), which consists of re-solving the deterministic surrogate problem at most $O(\log\log T)$ times. We prove the $\mathsf{BIRT}$ policy attains an $O(1)$ regret against the hindsight optimal egalitarian welfare, independently of the time horizon length $T$. We conclude by presenting numerical experiments to corroborate our theoretical claims and to illustrate the significant performance improvement against several benchmark policies.
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。