Hi! I'm Yi Feng (冯一). I've been a Ph.D. student at Shanghai University of Finance and Economics (SUFE) since 2021. My advisor is Prof. Xiao Wang. I'm also a student member of the Institute for Theoretical Computer Science.

My research mainly focuses on understanding learning dynamics in games and their applications to deep learning. Recently, I have been particuarlly attracted by the interaction between discrete-time algorithms and continuous-time dynamics.

"The fairest thing we can experience is the mysterious."

— Albert Einstein

Langevin Multiplicative Weights Update with Applications in Polynomial Portfolio Management (AAAI 2025)

Simple Combinatorial Construction of the k^o(1)-Lower Bound for Approximating the Parameterized k-Clique (SOSA 2025)

Prediction Accuracy of Learning in Games : Follow-the-Regularized-Leader meets Heisenberg (ICML 2024)

Last-iterate Convergence Separation between Extra-gradient and Optimism in Constrained Periodic Games (UAI 2024)

On the Last-iterate Convergence in Time-varying Zero-sum Games : Extra Gradient Succeeds where Optimism Fails (NeurIPS 2023)

Yi Feng, Hu Fu, Qun Hu, Ping Li, Ioannis Panageas, Bo Peng, Xiao Wang

Accelerated Multiplicative Weights Update Avoids Saddle Points almost always (IJCAI 2022)

Email: fengyi95524{at} gmail {dot} com

Address: Shanghai University of Finance and Economics, 100 Wudong Road, Shanghai, China, 200433.