用博弈论重新定义公平学习，让各群体协商最优预测模型。
Maximin Relative Improvement: Fair Learning as a Bargaining Problem
- 将公平性视为群体间的谈判问题，引入相对改进度量
- 相对改进实现尺度不变与个体单调性，优于传统绝对误差方法
- 理论证明在弱条件下有限样本收敛，适合多群体公平建模场景
在跨多个子群体部署单一预测器时，本文提出一种根本不同的方法：将群体公平性视为子群体间的博弈问题。这一博弈论视角揭示，现有鲁棒优化方法如最小化最差群体损失或后悔值，对应经典的谈判解决方案，并体现不同的公平原则。本文提出相对改进（relative improvement），即实际风险降低与基准预测器潜在降低之比，该度量可恢复卡尔-斯莫罗丁斯基（Kalai-Smorodinsky）解。相较于在群体可预测性不同时难以比较的绝对尺度方法，相对改进具有公理化依据，包括尺度不变性和个体单调性。在温和条件下，本文建立了有限样本收敛性保证。
原文摘要 · Abstract (English)
When deploying a single predictor across multiple subpopulations, we propose a fundamentally different approach: interpreting group fairness as a bargaining problem among subpopulations. This game-theoretic perspective reveals that existing robust optimization methods such as minimizing worst-group loss or regret correspond to classical bargaining solutions and embody different fairness principles. We propose relative improvement, the ratio of actual risk reduction to potential reduction from a baseline predictor, which recovers the Kalai-Smorodinsky solution. Unlike absolute-scale methods that may not be comparable when groups have different potential predictability, relative improvement provides axiomatic justification including scale invariance and individual monotonicity. We establish finite-sample convergence guarantees under mild conditions.
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。