3 papers
cs.LG2026
In-Run Data Shapley for Adam Optimizer
Meng Ding, Zeqing Zhang, Di Wang +1
Reliable data attribution is essential for mitigating bias and reducing computational waste in modern machine learning, with the Shapley value serving as the theoretical gold stand…
cs.LG2026
Differentially Private Non-convex Distributionally Robust Optimization
Difei Xu, Meng Ding, Zebin Ma +4
Real-world deployments routinely face distribution shifts, group imbalances, and adversarial perturbations, under which the traditional Empirical Risk Minimization (ERM) framework…
cs.LG2026
Understanding the Impact of Differentially Private Training on Memorization of Long-Tailed Data
Jiaming Zhang, Huanyi Xie, Meng Ding +3
Recent research shows that modern deep learning models achieve high predictive accuracy partly by memorizing individual training samples. Such memorization raises serious privacy c…