“…This issue has become a major obstacle to the deployment of machine learning systems in high-stakes domains, e.g., criminal judgment, medical testing, online advertising, hiring process, etc. To address these issues, it is crucial to understand the potential tradeoff between fairness and accuracy and develop fair machine learning algorithms (Zhao et al 2019;Hu et al 2023;Chi et al 2022Chi et al , 2021Wang, Li, and Zhao 2022;) that are optimal in terms of both efficiency and accuracy.…”