ESD Seminar by Chengchang Liu – Beyond optimal methods for minimax optimisation

Minimax optimisation has garnered significant attention in recent years due to its diverse applications in generative modelling, fairness-aware machine learning, game theory, and more. Various first- and second-order methods have been developed with “optimal” oracle complexities. In this talk, I will introduce several novel methods that achieve even faster convergence rates or better computational complexities compared to these optimal methods by effectively incorporating curvature information and leveraging the min-max structure. These results demonstrate that the min-max problem structure, which has been often ignored in prior research, can provably accelerate minimax optimisation.

Chengchang Liu is currently a PhD candidate at the Chinese University of Hong Kong (CUHK), supervised by Prof John C.S. Lui. His research interests include second-order optimisation, distributed optimisation, and the quantum optimisation. His research was awarded by COLT best student paper in 2025 and KDD best paper runner-up in 2022. His works have also been selected as oral or spotlight presentations at ICLR and NeurIPS. He is the recipient of the NSFC basic research scheme for PhD student (one of fourteen awardees in Hong Kong).

For more information about the ESD Seminar, please email esd_invite@sutd.edu.sg