Qianxiao Li
Assistant Professor at National University of Singapore
Schools
- National University of Singapore
Links
Biography
National University of Singapore
Qianxiao Li is an assistant professor in the Department of Mathematics, National University of Singapore. He graduated with a BA in mathematics from University of Cambridge and a PhD in applied mathematics from Princeton University. His research interests include the interplay of machine learning and dynamical systems, stochastic gradient algorithms and the application of data-driven methods to scientific problems. He is a recipient of the NRF fellowship, class of 2021.
Research Areas
- Machine Learning
- Deep Learning
- Numerical Analysis
- Optimization
- Control
Education
- Doctor of Philosophy - PhD Princeton University (2011 — 2016)
- Bachelor of Arts (B.A.) University of Cambridge (2007 — 2010)
Research Description
My research is on theoretical machine learning and its connections with numerical analysis, dynamical systems, and optimization/optimal control. I am also interested in developing novel applications of data-driven methods for scientific discovery.
Selected Publications
Li, Qianxiao, and Shuji Hao. “An Optimal Control Approach to Deep Learning and Applications to Discrete-Weight Neural Networks.” In Proceedings of the 35th International Conference on Machine Learning (ICML), 2018.
Li, Qianxiao, Cheng Tai, and Weinan E. “Stochastic Modified Equations and Adaptive Stochastic Gradient Algorithms.” In Proceedings of the 34th International Conference on Machine Learning (ICML), 2017.
Li, Qianxiao, Long Chen, Cheng Tai, and Weinan E. “Maximum Principle Based Algorithms for Deep Learning.” The Journal of Machine Learning Research 18, no. 1 (2018): 5998–6026.
Li, Qianxiao, Cheng Tai, and Weinan E. “Stochastic Modified Equations and Dynamics of Stochastic Gradient Algorithms I: Mathematical Foundations.” Journal of Machine Learning Research 20, no. 40 (2019): 1–47.
Cai, Yongqiang, Qianxiao Li, and Zuowei Shen. “A Quantitative Analysis of the Effect of Batch Normalization on Gradient Descent.” In International Conference on Machine Learning (ICML), 882–890, 2019.
Videos
Qianxiao Li: Gradient boosting and particle swarm optimization
On the Curse of Memory in Linear Recurrent Neural Networks
The Mathematics of Machine Learning: Assistant Professor Li Qianxiao
[MS130] Qianxiao Li: A Dynamical Systems Approach to Deep Learning (SIAM MDS 20)
Qianxiao Li | A mean-field optimal control formulation of deep learning
Read about executive education
Other experts
Popular Courses
The Manchester Leadership Development Programme
Alliance Manchester Business School
Manchester, United Kingdom
Jul 1
Private Equity: Investing and Creating Value
The Wharton School
Philadelphia, Pennsylvania, United States
Sep 8
Leading Digital Transformation
ESMT
Berlin, Germany
May 28
Leading Strategic Growth and Change
Columbia Business School
New York, New York, United States
Jun 10
The Positive Leader: Deep Change and Organizational Transformation
Stephen M. Ross School of Business
Ann Arbor, Michigan, United States
Jun 23
Leading People and Teams
ESMT
Berlin, Germany
May 28
Looking for an expert?
Contact us and we'll find the best option for you.