Selected works: 'On the global landscape of neural networks: an overview', 'Towards a better global loss landscape of GANs', NeurIPS 2020
Awards: Three papers accepted as spotlight papers at NeurIPS 2022 (~5% of >10,000 submissions)
Projects: Proved that the original Adam with proper hyperparameters can converge
Research Experience
Associate Professor, School of Data Science, Chinese University of Hong Kong, Shenzhen
Senior Research Scientist, Shenzhen Institute of Big Data (SRIBD)
Vice Chair, Shenzhen International Center for Industrial and Applied Mathematics (SICIAM)
Adjunct Associate Professor, UIUC
Assistant Professor, University of Illinois at Urbana-Champaign (2017-2022)
Visiting Researcher, Facebook Artificial Intelligence Research (2016.06-2016.12)
Post-doctoral Scholar, Stanford University (2015-2016)
Education
Ph.D. in Electrical Engineering, University of Minnesota (2009-2015)
B.Sc. in Mathematics, Peking University (2005-2009)
Post-doctoral Scholar, Stanford University (host: Yinyu Ye) (2015-2016)
Background
Associate Professor at Chinese University of Hong Kong, Shenzhen. Major interests are optimization and deep learning, especially large foundational models. Previously, a tenure-track assistant professor at UIUC and a full-time visiting scientist at FAIR (now Meta AI Fundamental AI Research). Recent interests include theory and algorithms of large foundation models, generative AI, learning-assisted optimization, and neural-net compression.
Miscellany
Recruiting: Multiple positions for research scientists, research engineers, postdocs, PhD students, visiting scholars, visiting students, and undergraduate interns.