Inherent Trade-Offs in Algorithmic Fairness
SIGMETRICS (Abstracts)(2019)
摘要
Recent discussion in both the academic literature and the public sphere about classification by algorithms has involved tension between competing notions of what it means for such a classification to be fair to different groups [1, 2, 5-7]. We consider several of the key fairness conditions that lie at the heart of these debates, and discuss recent research establishing inherent trade-offs between these conditions [3, 4, 8, 10, 14]. We also consider a variety of methods for promoting fairness and related notions for classification and selection problems that involve sets rather than just individuals [9, 11-13].
更多查看译文
关键词
algorithmic fairness, calibration
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要