[Past member] Postdoctoral Researcher (2023/2024)
kang.l.liu@fau.de
Room 03.362 | Friedrich-Alexander-Universität Erlangen-Nürnberg. FAU DCN-AvH Chair for Dynamics, Control, Machine Learning and Numerics – Alexander von Humboldt Professorship.
+49 9131 85-67133
I got my PhD within the DISCO group of Inria Saclay, under the supervision of L. Pfeiffer and J.F. Bonnans, and supported by Ecole Polytechnique. I obtained my master’s degree from Sorbonne University and my engineer’s degree from Ecole Polytechnique and my bachelor’s degree from Nanjing University.
After defending my doctoral thesis on October 5th, 2023 I am thrilled to start as postdoctoral researcher at the Chair for Dynamics, Control, Machine Learning, and Numerics at FAU.
My research focuses on the following topics:
1. Large-scale non-convex optimization and mean field optimization;
2. Mean field games with a particular emphasis on numerical methods;
3. Optimal control and machine learning, etc.
PhD Thesis: Numerical analysis and methods for mean-field-type optimization problems (Oct. 2023)
Events
• FAU DCN-AvH Seminar (Feb. 08, 2024): Non-convex aggregative optimization problems and their mean-field relaxation.
Publications
2025
A Potential Game Perspective in Federated Learning
(2025)
DOI: 10.48550/arXiv.2411.11793
URL: https://arxiv.org/abs/2411.11793
BibTeX: Download , , :
Representation and Regression Problems in Neural Networks: Relaxation, Generalization, and Numerics
(2025)
Open Access: https://arxiv.org/html/2412.01619v1
BibTeX: Download , :
2024
Universal Approximation of Dynamical Systems by Semi-Autonomous Neural ODEs and Applications
(2024)
Open Access: https://arxiv.org/abs/2407.17092
URL: https://arxiv.org/abs/2407.17092
BibTeX: Download , , , :