From Pseudorandomness to Multi-Group Fairness and Back
It addresses fairness in machine learning for diverse groups, with incremental contributions through new connections and algorithms.
The paper tackles the problem of multi-group fairness in prediction algorithms by connecting it to pseudorandomness concepts, resulting in new, more efficient algorithms for multicalibration and novel graph theoretic results.
We identify and explore connections between the recent literature on multi-group fairness for prediction algorithms and the pseudorandomness notions of leakage-resilience and graph regularity. We frame our investigation using new variants of multicalibration based on statistical distance and closely related to the concept of outcome indistinguishability. Adopting this perspective leads us not only to new, more efficient algorithms for multicalibration, but also to our graph theoretic results and a proof of a novel hardcore lemma for real-valued functions.