论文标题
公平
Metrizing Fairness
论文作者
论文摘要
我们研究了监督的学习问题,这些问题对两个人群群体具有重大影响,并且我们寻求有关群体公平标准(例如统计平等)(SP)等群体公平标准的预测因素。如果两组内的预测分布在Kolmogorov距离内接近,则预测因子是SP-FAIR,并且通过惩罚这两个分布在学习问题的目标函数中的差异来实现公平性。在本文中,我们确定了确保坚硬限制的条件,以提高预测准确性。我们还展示了除Kolmogorov距离以外的其他概率指标(IPM)的概念和计算益处。从概念上讲,我们表明,任何IPM的生成器都可以解释为一个实用程序功能家族,并且如果两个人口组中的个人有不同的预期公用事业,那么就此IPM而言,就会出现不公平。我们还证明,如果不公平的梯度估计量不公平的预测损失允许由随机的小批次训练样本构建,如果不公平的训练样本,则是由平方$ \ MATHCAL l^2 $ dESTANCE衡量的,或者是通过平方的最大平均差异来构建的。在这种情况下,公平学习问题容易受到有效的随机梯度下降(SGD)算法的影响。关于合成和真实数据的数值实验表明,这些SGD算法的表现优于公平学习的最先进方法,因为它们实现了卓越的准确性 - 不足的权衡 - 有时更快的数量级。
We study supervised learning problems that have significant effects on individuals from two demographic groups, and we seek predictors that are fair with respect to a group fairness criterion such as statistical parity (SP). A predictor is SP-fair if the distributions of predictions within the two groups are close in Kolmogorov distance, and fairness is achieved by penalizing the dissimilarity of these two distributions in the objective function of the learning problem. In this paper, we identify conditions under which hard SP constraints are guaranteed to improve predictive accuracy. We also showcase conceptual and computational benefits of measuring unfairness with integral probability metrics (IPMs) other than the Kolmogorov distance. Conceptually, we show that the generator of any IPM can be interpreted as a family of utility functions and that unfairness with respect to this IPM arises if individuals in the two demographic groups have diverging expected utilities. We also prove that the unfairness-regularized prediction loss admits unbiased gradient estimators, which are constructed from random mini-batches of training samples, if unfairness is measured by the squared $\mathcal L^2$-distance or by a squared maximum mean discrepancy. In this case, the fair learning problem is susceptible to efficient stochastic gradient descent (SGD) algorithms. Numerical experiments on synthetic and real data show that these SGD algorithms outperform state-of-the-art methods for fair learning in that they achieve superior accuracy-unfairness trade-offs -- sometimes orders of magnitude faster.