About
I am an (non-tenured) associate professor of Institute for Theoretical Computer Science at SUFE. Before joining SUFE, I did my postdoc at SUTD under supervision of Georgios Piliouras and Ioannis Panageas. I got my B.S. from China University of Geosciences (Beijing) and Ph.D in Mathematics from University at Buffalo, advised by Mohan Ramachandran. From 2026 to 2027, I am serving as Deputy Director (on secondment) of the Department of Development and Planning.Contact
Email: wangxiao@sufe.edu.cnAddress: Shanghai University of Finance and Economics 100 Wudong Road, Shanghai, China, 200433.
act.
The act (Algorithmic Creativity Team) is a research group that offers interdisciplinary research projects (not publication-oriented) to students. Our research is organized around two complementary directions regarding students' backgrounds and interests:News
5.1.2026: Four submissions rejected by ICML, including one desk reject.Ph.D Students
Pingfan Wu, Fall 2025-presentWeiming Ou, Fall 2023-present
Yi Feng, Fall 2021-Spring 2025, DDSA Postdoc Fellow at Danish Data Science Academy, Denmark
Teaching
Fall 2026: Mathematical Foundation for AI (Undergrad).
AI generated course companion:
Diffusion
Dynamical Systems
.
1:Curves and Surfaces 2:Differentiable Manifolds and Mappings 3:Riemannian Geometry 4:Simplicial and Persistent Homology 5:Riemannian Gradient and Newton's Methods
Spring 2025: Linear Algebra (Pilot class).
Publications
- Payoff-Aware Prediction of Population Game Dynamics
with Kang Wang and Renzhe Xu,
NeurIPS 2026. - Rectifying Categorical Flows on Statistical Manifolds for One-Step Generation
with Xiaohuan Jia, Renzhe Xu, Jiayun Wu and Shaohua Fan,
NeurIPS 2026. - Revisiting AdaGrad in Stochastic Convex Optimization: Last Iterates,
High Probability, and Lower Bounds
with Weiming Ou,
arxiv. - Tight Sampling Complexity with stochastic gradient oracles in Fixed
Dimensions
with Weiming Ou,
arxiv. - Heavy-Tailed First-Order Optimization for Polyak-Łojasiewicz
Condition: High-Dimensional Minimax Bounds, High-Probability
Guarantee, and Fixed-Dimensional Improvements
with Weiming Ou,
arxiv. - Understanding Dynamics of Adam in Zero-Sum Games: An ODE Approach
with Yi Feng and Weiming Ou,
ICML 2026. - Heterogeneous Learning Mechanisms in Zero-Sum Games: From Best-Iterate to Last-Iterate Convergence
with Xinxiang Guo, Junyue Zhang, Yifen Mu and Ioannis Panageas,
International Federation of Automatic Control (IFAC 2026). - Last-iterate Convergence of Heterogeneous Learning in Time-Varying Zero-Sum Games
with Junyue Zhang, Xinxiang Guo, Yi Feng and Yifen Mu,
AAMAS 2026. - On Perturbed Natural Adaptive Gradient Descent and its Applications in Portfolio Optimization
with Y. Cai, H. Liang, Y. Qiu, T. Xie, and Z. Zhao,
ECAI 2025. - Continuous-Time Analysis of Heavy Ball Momentum in Min-Max Games
with Yi Feng, Kaito Fujii, Stratis Skoulakis, and Volkan Cevher,
ICML 2025. - Langevin Multiplicative Weights Update with Applications in Portfolio Management
with Yi Feng and Tian Xie,
AAAI 2025. - Prediction Accuracy of Learning in Games : Follow-the-Regularized-Leader meets Heisenberg
with Yi Feng and Georgios Piliouras,
ICML 2024. - Riemannian Accelerated Zeroth-order Algorithm: Improved Robustness and Lower Query Complexity
with Chang He, Zhaoye Pan and Bo Jiang,
ICML 2024. - Last-iterate Convergence Separation between Extra-gradient and Optimisim in Constrained Periodic Game
with Yi Feng, Ping Li and Ioannis Panageas,
UAI 2024. - On the Last-iterate Convergence in Time-varying Zero-sum Games: Extra Gradient Succeeds where Optimism Fails
with Yi Feng, Hu Fu, Qun Hu, Ping Li, Ioannis Panageas and Bo Peng,
NeurIPS 2023. - Embedding Surfaces by Optimizing Neural Networks with Prescribed Riemannian Metric and Beyond,
with Yi Feng, Sizhe Li, and Ioannis Panageas,
ICML 2023 Workshop Frontiers4LCD. - Semi Bandit dynamics in Congestion Games: Convergence to Nash Equilibrium and No-Regret Guarantees,
with Ioannis Panageas, Efstratios Panteleimon Skoulakis, Luca Viano and Volkan Cevher,
ICML 2023 (Oral). - AdaGrad Avoids Saddle Points,
with Kimon Antonakopoulos, Panayotis Mertikopoulos and Georgios Piliouras,
ICML 2022.
(A mistake has been found, correction needed!) - Accelerated Multiplicative Weights Update Avoids Saddle Points almost always,
with Yi Feng and Ioannis Panageas,
IJCAI 2022. - Constants of Motion: The Antidote to Chaos in Optimization and Game Dynamics,
with Georgios Piliouras,
arXiv. - Last iterate convergence in no-regret learning: constrained min-max optimization for convex-concave landscapes,
with Qi Lei, Sai Ganesh Nagarajan and Ioannis Panageas,
AISTATS 2021. - Fast convergence of Langevin dynamics on manifold: Geodesics meet log-Sobolev,
with Qi Lei and Ioannis Panageas,
NeurIPS 2020. - Convergence to second-order stationarity for non-negative matrix factorization: Provably and concurrently,
with Ioannis Panageas, Stratis Skoulakis and Antonis Varvitsiotis,
arXiv. - Depth-width trade-offs for ReLU networks via Sharkovsky's theorem,
with Vaggos Chatziafratis, Sai Ganesh Nagarajan and Ioannis Panageas,
ICLR 2020 (spotlight), Video (Speaker: Ioannis Panageas, MiFODS Workshop, MIT, Jan 27-29, 2020). - First-order methods almost always avoid saddle points: the case of vanishing stepsize,
with Ioannis Panageas and Georgios Piliouras,
NeurIPS 2019, Poster. - Multiplicative weights update as a distributed constrained optimization algorithm:
converges to second-order stationary points almost always,
with Ioannis Panageas and Georgios Piliouras,
ICML 2019, Poster, Slides (Speaker: Xiao Wang). - Kazhdan's property (T) and structure for locally symmetric spaces,
Submitted
Visitors Hosted
- Vaggos Chatziafratis, Assistant Professor of Computer Science, UC Santa Cruz — November 2026.
- Victor Shim, Emeritus Professor of Applied Mechanics, National University of Singapore — September 2026.
- Antonios Varvitsiotis, Associate Professor of Engineering Systems and Design, Singapore University of Technology and Design — August 2026.
- Trung Tuyen Truong, Professor of Mathematics, University of Oslo — July 2026.
- Andrea Paudice, Assistant Professor of Computer Science, Aarhus University — June 2026.
- Yannis Panageas, Associate Professor of Computer Science, University of California, Irvine — June 2026.
- Kaito Fujii, Senior Lecturer, Kyoto University — June 2026.
- Sai Ganesh Nagarajan, Assistant Professor of Computer Science, University of Southern Denmark — June 2026.
- Kang Zhang, Professor of Computational Media and Arts, The Hong Kong University of Science and Technology (Guangzhou) — December 2025.
- Yershat Sapazhanov, Associate Professor of Applied Mathematics, Narxoz University — November 2025.
- Stratis Skoulakis, Assistant Professor of Computer Science, Aarhus University — March 2025.
- Yannis Panageas, Assistant Professor of Computer Science, University of California, Irvine — January 2025.