中文摘要
决策者通常 (i) 利用训练数据来学习各处理的相对有效性, 并 (ii) 根据某个目标泛函选择一种蕴含“最优”预测结果分布的实施机制。然而, 关注公平性的决策者可能不会满足于以对总体中某一子群体“不公平”为代价来实现上述最优性, 即该子群体的结果分布与整体最优结果分布偏离过大。我们研究了一个框架, 该框架允许决策者对此类偏离进行正则化, 同时可运用广泛的目标泛函与公平性度量。我们为带有 (可能由) 数据驱动的偏好参数的经验成功政策 (empirical success policies) 建立了遗憾 (regret) 与一致性保证, 并提供了数值结果。此外, 我们在两个实证情境中简要说明了这些方法。
Abstract
A decision maker typically (i) incorporates training data to learn about the relative effectiveness of treatments, and (ii) chooses an implementation mechanism that implies an “optimal” predicted outcome distribution according to some target functional. Nevertheless, a fairness-aware decision maker may not be satisfied achieving said optimality at the cost of being “unfair” against a subgroup of the population, in the sense that the outcome distribution in that subgroup deviates too strongly from the overall optimal outcome distribution. We study a framework that allows the decision maker to regularize such deviations, while allowing for a wide range of target functionals and fairness measures to be employed. We establish regret and consistency guarantees for empirical success policies with (possibly) data-driven preference parameters, and provide numerical results. Furthermore, we briefly illustrate the methods in two empirical settings.