arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.01111cs.GTcs.LG
收藏

无货币资源分配的正则化比例公平机制

Regularized Proportional Fairness Mechanism for Resource Allocation Without Money

JPMorgan AI Research(摩根大通人工智能研究院)

Sihan Zeng, Sujay Bhatt, Alec Koppel, Sumitra Ganesh

AI总结:

针对无货币资源分配中比例公平机制可利用性过高的问题,本文提出正则化比例公平网络RPF-Net,通过学习最可利用分配来正则化PF输出,在保持社会福利的同时降低虚报激励,并给出泛化保证与实验验证。

摘要:

资源分配中的机制设计研究如何在自利智能体之间分配有限资源,其中智能体对分配的满意度取决于其私有效用。我们在无支付环境中考虑该问题,目标是在保证激励相容(IC)的同时最大化社会福利,即智能体不能通过虚报效用而夸大其获得的分配。众所周知的比例公平(PF)机制能够实现最大可能的社会福利,但会带来不理想的高可利用性(即虚报效用所导致的效用最大单边膨胀,是偏离IC程度的一种度量)。事实上,已知在不使用货币激励的情况下,没有任何机制能够同时实现最大社会福利和精确激励相容(IC)(Cole等人,2013)。受这一事实的启发,我们提出学习一种近似机制,以理想地在相互竞争的目标之间进行权衡。我们的主要贡献是设计了一种针对资源分配问题的创新神经网络架构,我们将其命名为正则化比例公平网络(RPF-Net)。RPF-Net通过一个学习得到的、对最可利用分配进行逼近的函数来正则化PF机制的输出,目的是降低任何智能体虚报效用的激励。我们推导了泛化边界,保证机制在有限样本和分布外样本下训练时的性能,并通过实验证明了所提机制相对于最先进方法的优点。

英文摘要:

Mechanism design in resource allocation studies dividing limited resources among self-interested agents whose satisfaction with the allocation depends on privately held utilities. We consider the problem in a payment-free setting, with the aim of maximizing social welfare while enforcing incentive compatibility (IC), i.e., agents cannot inflate allocations by misreporting their utilities. The well-known proportional fairness (PF) mechanism achieves the maximum possible social welfare but incurs an undesirably high exploitability (the maximum unilateral inflation in utility from misreport and a measure of deviation from IC). In fact, it is known that no mechanism can achieve the maximum social welfare and exact incentive compatibility (IC) simultaneously without the use of monetary incentives (Cole et al., 2013). Motivated by this fact, we propose learning an approximate mechanism that desirably trades off the competing objectives. Our main contribution is to design an innovative neural network architecture tailored to the resource allocation problem, which we name Regularized Proportional Fairness Network (RPF-Net). RPF-Net regularizes the output of the PF mechanism by a learned function approximator of the most exploitable allocation, with the aim of reducing the incentive for any agent to misreport. We derive generalization bounds that guarantee the mechanism performance when trained under finite and out-of-distribution samples and experimentally demonstrate the merits of the proposed mechanism compared to the state-of-the-art.

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。

↑