This seminar aims to introduce cutting-edge research of Data Science, especially, the application of Data Science in scientific problems and the "science" part of Data Science, such as understanding deep learning. Welcome to contact Zhiqin Xu (xuzhiqin@sjtu.edu.cn).
A Statistical Mechanics Theory of Generalization in Kernel Regression and Wide Neural Networks
Cengiz Pehlevan, Harvard University
2020.06.26, 10:00-11:00

Understanding Deep Learning via Analyzing Trajectories of Gradient Descent
Wei Hu, Princeton University
2020.06.18, 10:30-11:30

An Alternative View: When does SGD Escape Local Minima?
Yang Yuan, Tsinghua University
2020.06.17, 15:30-16:30

Generalization Error of Linearized Neural Networks: Staircase and Double-Descent
Song Mei,Stanford University
2020.06.11, 10:30-11:30

Neural Tangent Kernel: Convergence and Generalization of DNNs
Arthur Jacot,Ecole polytechnique fédérale de Lausanne (EPFL)
2020.05.28, 20:30-21:30

Approximating Quantum Many-Body Wave Functions using Artificial Neural Networks
Zi Cai, School of Physics and Astronomy, Shanghai Jiao Tong University
2020.05.21, 10:30-11:30

Second-Order Type Stochastic Optimization Algorithms for Machine Learning
Zaiwen Wen, Peking University
2020.05.15, 10:30-11:30

Neural Fokker-Planck Equation
Wuchen Li, UCLA Department of Mathematics
2020.05.05, 10:30-11:30

Partial Differential Equation Principled Trustworthy Deep Learning
Bao Wang, University of California, Los Angeles
2020.04.23, 10:30-11:30

The Tradeoffs and Layered Architecture in Brain
Quanying Liu, Southern University of Science and Technology
2020.04.08, 14:00-15:00

Finite Elements and Deep Neural Networks
Juncai He, Penn State University
2020.03.27, 10:00-11:00

A-Priori Estimates of Population Risks for Neural Networks Models
Chao Ma, Princeton University
2020.03.19, 10:00-11:00