用可计算的公平性机制，让AI资源分配更均衡且稳定。
Computable Fairness: Boltzmann-Softmax Control for AI Resource Allocation
- 将Boltzmann-Softmax改造成概率分配工具，通过β参数调控效率与公平性平衡。
- 动态控制算法AHC++能抑制极端资源集中，保持接近恒定的系统总损失。
- 适用于大规模并发AI任务调度，对高扩展性有强支撑。
在大规模AI系统中，如何在多个智能体间分配稀缺资源（如GPU计算时间与带宽）是一项关键挑战。传统策略侧重效率指标，可能导致资源垄断，损害系统多样性与稳定性。本文提出可计算公平分配（CFD）框架，将Boltzmann-Softmax函数重新诠释为概率资源分配机制，将逆温度参数β作为可计算的控制变量，调节效率与公平性的权衡。静态分析显示存在帕累托前沿，其“近最优稳定区间”内总损失在不同策略权重下基本保持不变。在动态设置中，AHC++（自适应硬上限控制器++）实时更新β，以观测到的资源支配度与目标之间的误差为反馈。仿真表明，AHC++在外部冲击下有效抑制极端资源集中，同时维持公平性目标，且吞吐量下降有限。可扩展性分析证实，智能体数量增加100倍，执行时间仅增加约5.5倍。代码已开源：https://github.com/entrofy-ai/computable-fairness
原文摘要 · Abstract (English)
In large-scale AI systems, allocating scarce resources such as GPU compute time and bandwidth among multiple agents is a critical challenge. Conventional policies focus on efficiency metrics, potentially leading to dominance concentration that undermines system diversity and stability. We propose Computable Fair Division (CFD), a framework that reinterprets the Boltzmann-Softmax function not as a selection tool but as a probabilistic resource allocation mechanism, redefining the inverse temperature parameter $β$ as a computable control variable governing the efficiency-fairness balance. Static analysis reveals a Pareto frontier with a near-optimal Stability Corridor where total loss remains approximately constant across policy weights. In the dynamic setting, AHC++ (Adaptive Hard-Cap Controller++) updates $β$ in real time using the error between observed dominance and a policy-specified target as feedback. Simulations show that AHC++ suppresses extreme dominance concentration under exogenous shocks while tracking fairness targets without substantial throughput degradation. Scalability analysis confirms that a 100x increase in agents yields only approximately 5.5x increase in execution time. Code: https://github.com/entrofy-ai/computable-fairness
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。