Fair and Optimal Prediction via Post-Processing

In this talk I will discuss our recent work on characterizing the inherent tradeoff between fairness and accuracy in both classification and regression problems. I will also present a post-processing algorithm that derives optimal fair predictors from Bayes score functions.

Authors

• Han Zhao Zhejiang University Westlake University

Keywords

• Algorithmic Fairness
• Domain Generalization
• Robustness
• Trustworthy Machine Learning