Tengyuan Liang

Biography

Tengyuan Liang is a Professor of Econometrics and Statistics, and Applied AI at The University of Chicago Booth School of Business. He builds mathematical theories for modern AI—theories that reveal when and why these systems work—and creates principled tools for their reliable application in business and economics. His work on the interpolation regime, generative models, and causal inference spans journals across statistics, machine learning, economics, and applied mathematics.

His research has established the role of implicit regularization in overparametrized learning—from kernel machines to boosting to neural networks; built statistical and computational foundations for generative models, including GANs, diffusion models, and PDE-based samplers; and developed machine learning methods for causal inference and uncertainty quantification.

He holds a B.Sc. in Mathematics from Peking University and a Ph.D. in Statistics from the Wharton School, University of Pennsylvania, where he received the J. Parker Bursk Memorial Prize and a Winkelman Fellowship. He is a recipient of the National Science Foundation CAREER Award from the Division of Mathematical Sciences.

He has served as Associate Editor for the Journal of the American Statistical Association and Operations Research, on the Editorial Board of the Journal of Machine Learning Research, and on the Senior Program Committee for the Conference on Learning Theory.

Beyond Booth, he has been a Research Scientist at Yahoo Research in New York, a Visiting Professor at the Cowles Foundation at Yale University, and a Global Faculty in Residence at The University of Chicago Hong Kong Campus.

Academic Areas

• Econometrics and Statistics
• Applied AI