On Fairness and CalibrationEI

摘要

The machine learning community has become increasingly concerned with the potential for bias and discrimination in predictive models. This has motivated a growing line of work on what it means for a classification procedure to be fair. In this paper, we investigate the tension between minimizing error disparity across different population groups while maintaining calibrated probability estimates. We show that calibration is compatible only with a single error constraint (i.e. equal false-negatives rates across groups), and show that a...更多
个人信息

 

您的评分 :

NIPS, pp. 5684-5693, 2017.

被引用次数38|引用|8
标签
作者
评论