Zihang Xiang

Improved Rates of Differentially Private Nonconvex-Strongly-Concave Minimax Optimization

2025 · Proceedings of the AAAI Conference on Artificial Intelligence

In this paper, we study the problem of (finite sum) minimax optimization in the Differential Privacy (DP) model. Unlike most of the previous studies on the (strongly) convex-concave settings or loss functions satisfying the Polyak-Lojasiewicz …