I am a Postdoctoral Researcher in the Deep Learning Theory Team at RIKEN AIP, where I am very fortunate to work with Prof. Taiji Suzuki. I received my Ph.D. from the Department of Systems Engineering and Engineering Management from the Chinese University of Hong Kong, under the supervision of Prof. Anthony Man-Cho So, to whom I am deeply grateful for his guidance and support. During my Ph.D, from September 2024 to January 2025, I also had the privilege of visiting the Department of Combinatorics and Optimization at University of Waterloo, supervised by Prof. Stephen A. Vavasis and Prof. Henry Wolkowicz. Before that, I received my bachelor degree in Statistics from Huazhong University of Science and Technology in 2020. My research involves developing algorithms for structured nonconvex problems and provide theoretical analysis for them.
Optimal Deterministic First-Order Oracle Complexity for Nonconvex-Concave Minimax Optimization
Siyu Pan, Taoli Zheng, and Jiajin Li.
Last-Iterate Convergence of Single-Loop Stochastic Methods for Constrained Convex-Concave Minimax Problems [NeurIPS 2026]
Taoli Zheng, Jiajin Li, and Anthony Man-Cho So.
Doubly smoothed optimistic gradients: A universal approach for smooth minimax problems
Taoli Zheng, Anthony Man-Cho So, and Jiajin Li.
Universal Gradient Descent Ascent Method for Nonconvex-Nonconcave Minimax Optimization [NeurIPS 2023]
Taoli Zheng, Linglingzhi Zhu, Anthony Man-Cho So, José Blanchet, Jiajin Li.