Fair regression via plug-in estimator and recalibration with statistical guarantees
Fair regression via plug-in estimator and recalibration with statistical guarantees
复制标题
通过插件估计器进行公平回归并通过统计保证进行重新校准
DOI：
--
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
M. Pontil
中科院分区：
文献类型：
--
作者：
Evgenii Chzhen;Christophe Denis;Mohamed Hebiri;L. Oneto;M. Pontil
我们研究学习受公平约束的最优回归函数的问题。它要求，在敏感特征的条件下，函数输出的分布保持不变。此约束自然地将常用于分类的人口统计平等概念扩展到回归设置。我们通过利用代理离散化版本来解决这个问题，为此我们推导出最佳公平预测器的显式表达式。这个结果自然表明了一种两阶段方法，其中我们首先根据一组标记数据估计（无约束）回归函数，然后用另一组未标记数据重新校准它。通过平滑的优化可以有效地执行重新校准步骤。我们从风险和公平约束方面推导了所提出的估计器到最优公平预测器的收敛率。最后，我们提出了数值实验，表明所提出的方法通常优于最先进的方法或具有竞争力。
We study the problem of learning an optimal regression function subject to a fairness constraint. It requires that, conditionally on the sensitive feature, the distribution of the function output remains the same. This constraint naturally extends the notion of demographic parity, often used in classification, to the regression setting. We tackle this problem by leveraging on a proxy-discretized version, for which we derive an explicit expression of the optimal fair predictor. This result naturally suggests a two stage approach, in which we first estimate the (unconstrained) regression function from a set of labeled data and then we recalibrate it with another set of unlabeled data. The recalibration step can be efficiently performed via a smooth optimization. We derive rates of convergence of the proposed estimator to the optimal fair predictor both in terms of the risk and fairness constraint. Finally, we present numerical experiments illustrating that the proposed method is often superior or competitive with state-of-the-art methods.
学习最佳公平政策。
DOI：
--
发表时间：
2019
期刊：
Proceedings of machine learning research
影响因子：
--
作者：
Nabi,Razieh;Malinsky,Daniel;Shpitser,Ilya
通讯作者：
Shpitser,Ilya