Learning Non-Discriminatory Predictors
Learning Non-Discriminatory Predictors
复制标题
DOI：
--
复制
发表时间：
2017-02
期刊：
影响因子：
--
通讯作者：
Blake E. Woodworth;Suriya Gunasekar;Mesrob I. Ohannessian;N. Srebro
中科院分区：
文献类型：
--
作者：
Blake E. Woodworth;Suriya Gunasekar;Mesrob I. Ohannessian;N. Srebro
根据Hardt等人[2016]提出的“均等几率”概念，我们考虑学习一个对“受保护属性”没有歧视的预测器。我们从统计和计算两方面研究了从有限的训练集中学习这种非歧视性预测器的问题。我们表明，正如Hardt等人所建议的那样，事后修正方法可能是高度次优的，提出了一个近乎最优的统计过程，认为相关的计算问题是棘手的，并建议对学习是可处理的非歧视定义的第二时刻放松。
We consider learning a predictor which is non-discriminatory with respect to a "protected attribute" according to the notion of "equalized odds" proposed by Hardt et al. [2016]. We study the problem of learning such a non-discriminatory predictor from a finite training set, both statistically and computationally. We show that a post-hoc correction approach, as suggested by Hardt et al, can be highly suboptimal, present a nearly-optimal statistical procedure, argue that the associated computational problem is intractable, and suggest a second moment relaxation of the non-discrimination definition for which learning is tractable.