Peter X.‐K. Song

A Differentially Private Weighted Empirical Risk Minimization Procedure and Its Application to Outcome Weighted Learning

2026 · IEEE Transactions on Information Forensics and Security

Data used to train predictive models via empirical risk minimization (ERM) often contain sensitive personal information. While differential privacy (DP) provides mathematically provable bounds to protect such data, previous work has focused almost exclusively on …