Wei Hu is an Assistant Professor at the University of Michigan with a focus on the theoretical foundations of deep learning. His research aims to uncover the underlying mechanisms and principles of deep learning, often referred to as opening the black box of neural networks. His approach involves a blend of theory and empirical analysis, addressing clean and controlled problems related to complex real-world models. Hu completed his PhD at Princeton University, under the mentorship of Sanjeev Arora and holds a bachelor’s degree from Tsinghua University. He has contributed to multiple high-impact publications, exploring areas such as benign overfitting, learning representations, and theoretical underpinnings of machine learning techniques. Hu's scholarship has been recognized through various awards, including the AAAI New Faculty Highlights in 2024 and the Google Research Scholar Award in 2023. In addition to his research, he is also active in academic service, having served as an area chair for major conferences like ICML and NeurIPS.
FODSI • PRINCETON
Conducted research in deep learning and machine learning, focusing on theoretical aspects.
University of Michigan • Ann Arbor, MI
Teaching and conducting research in deep learning and machine learning.