2 papers
cs.LG2025
From Pseudorandomness to Multi-Group Fairness and Back
Cynthia Dwork, Daniel Lee, Huijia Lin +1
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…
cs.LG2025
Architecture Selection via the Trade-off Between Accuracy and Robustness
Zhun Deng, Cynthia Dwork, Jialiang Wang +1
We provide a general framework for characterizing the trade-off between accuracy and robustness in supervised learning. We propose a method and define quantities to characterize th…