Areas of Focus
- 深度学习数学理论
Work Experience
- 2021.12-现在 - 北京大学 - 助理教授
- 2021.8-2021.11 - 宾夕法尼亚大学 - 博士后
- 2018.11-2021.7 - 普林斯顿大学 - 博士后
Academic Background & Achievements
- 2019 博士: 北京大学
- 2012 学士: 南开大学
Publications
- Machine Learning from a Continuous Viewpoint, 魏南, 马超, 吴磊, 2020
- Barron spaces and flow-induced function spaces for neural network models, 魏南, 马超, 吴磊, 2021
- A comparative analysis of the optimization and generalization property of two-layer neural network and random feature models under gradient descent dynamics, 魏南, 马超, 吴磊, 2020
- A priori estimates of the population risk for two-layer neural networks, 魏南, 马超, 吴磊, 2019
- How SGD selects the global minima in over-parameterized learning: A dynamical stability perspective, 吴磊, 马超, 魏南, 2018
