Mo Zhou (mozhou717@gmail.com) https://mozhou7.github.io is an IFDS postdoc (started October 2024) at the University of Washington working with Simon Du and Maryam Fazel. He received his Ph.D. in Computer Science from Duke University, advised by Rong Ge.
Mo’s research focuses on the mathematical foundations of machine learning, particularly in optimization related deep learning theory. His work involves analyzing the training dynamics of overparametrized models in the feature learning regime to uncover underlying mechanisms. He also investigates phenomena observed in deep learning practice by theoretically analyzing simplified models and making predictions based on these insights.