MSEE 112
Webinar
Tuesday, October 3, 2023 12:00 Noon.
To mitigate the bias exhibited by machine learning models, fairness criteria can be integrated into the training process to ensure fair treatment across all demographics, but it often comes at the expense of model performance. Understanding such tradeoffs, therefore, underlies the design of optimal and fair algorithms. In this talk, I will first discuss our recent work on characterizing the inherent tradeoff between fairness and accuracy in both classification and regression problems, where we show that the cost of fairness could be characterized by the optimal value of a Wasserstein-barycenter problem. Then I will show that the complexity of learning the optimal fair predictor is the same as learning the Bayes predictor and present a post-processing algorithm based on the solution to the Wasserstein-barycenter problem that derives the optimal fair predictors from Bayes score functions
Continue reading