Hancheng Min
Postdoctoral Researcher, ESE '23-'25 - Associate Professor, Shanghai Jiao Tong University
Hancheng Min was a Postdoc Researcher at the University of Pennsylvania, advised by Prof. René Vidal. Prior to joining Penn, he received his Ph.D. degree in Electrical and Computer Engineering at Johns Hopkins University, advised by Prof. Enrique Mallada. He received MINDS Fellowship in 2020-2021. His research interests include deep learning theory, analysis and control of large-scale networks, and safe reinforcement learning.
Publications
Publisher IEEE Signal Processing Magazine
Convergence Rates for Gradient Descent on the Edge of Stability for Overparametrised Least Squares
Publisher NeurIPS
Neural Collapse under Gradient Flow on Shallow ReLU Networks for Orthogonally Separable Data
Publisher NeurIPS
Publisher CDC
A Local Polyak-Lojasiewicz and Descent Lemma of Gradient Descent For Overparametrized Linear Models
Publisher ArXiv
Publisher ArXiv
Early Neuron Alignment in Two-layer ReLU Networks with Small Initialization
Publisher International Conference on Learning Representations
News
Rachleff University Professor - Radiology, Perelman School of Medicine; ESE, Penn Engineering