JP Gan Professor of Econometrics and Statistics in the Wallman Society of Fellows
Tengyuan Liang is a Professor of Econometrics and Statistics at the University of Chicago Booth School of Business. Professor Liang's research focuses on problems at the intersection of inference, learning, and optimization. He has published in leading journals and venues in economics, statistics, machine learning, and applied mathematics. He is a recipient of the National Science Foundation CAREER Award.
He earned a Ph.D. in Statistics from the Wharton School at the University of Pennsylvania and a B.Sc. in Mathematics from Peking University. He was awarded聽the J. Parker Memorial Bursk Prize and a Winkelman Fellowship聽from the Wharton School.
In past work, he has uncovered the presence and effects of implicit regularization in kernel machines, boosting methods, and neural networks in high-dimensional and over-parametrized regimes. He has developed statistical and computational theories for generative models, including generative adversarial networks, probabilistic diffusion models, and PDE-based stochastic samplers. He has contributed to the rigorous application of machine learning and optimization techniques in causal inference and uncertainty quantification.
He served as an Associate Editor for prestigious journals, including the聽Journal of the American Statistical Association, and聽the Operations Research, on the Editorial Board of the聽Journal of Machine Learning Research,聽and聽the Senior Program Committee for the聽Conference on Learning Theory.
Beyond his role at the University of Chicago, Professor Liang has experience as a Research Scientist at Yahoo! Research in New York, where he worked on large-scale machine learning applications. He also served as a short-term Visiting Professor in Econometrics at the Cowles Foundation for Research in Economics at Yale University.
| Number | Course Title | Quarter |
|---|---|---|
| Business Statistics | 2025 (Winter) | |
| Data, Learning, and Algorithms | 2025 (Winter) |
Machine learning is being tasked with an increasing number of important decisions. But the answers it generates involve a degree of uncertainty.
{PubDate}
Evaluating the performance of machine-learning tools isn’t always easily done.
{PubDate}