Professor Tengyuan Liang has been awarded the National Science Foundation CAREER grant, the organization's most prestigious junior faculty award. The Faculty Early Career Development (CAREER) Program supports early-career faculty who have the potential to serve as academic role models in research and education and to lead advances in the mission of their department or organization.
Liang will be principal investigator on the grant entitled, "CAREER – New Statistical Paradigms Reconciling Empirical Surprises in Modern Machine Learning." The goal of Liang’s proposed research is to develop new statistical and computational paradigms that bridge the gap between theory and practice for learning from data. Liang will investigate the role of model regularization, statistical performance, and optimization algorithms in high- or infinite-dimensional machine learning models.
“Empirical phenomena exhibited by modern machine learning models constantly challenge our theoretical foundations in statistics and computation.” Liang said. “I attempt to advance the present state of knowledge on how such models extract information effectively from data.”
The project will also significantly impact undergraduate and graduate students’ training in data science research through synergetic educational and research activities to be hosted under a new initiative that integrates and enhances resources across the fields of statistics and economics.
“Empirical phenomena exhibited by modern machine learning models constantly challenge our theoretical foundations in statistics and computation. I attempt to advance the present state of knowledge on how such models extract information effectively from data.”
Liang is an assistant professor of econometrics and statistics and the George C. Tiao Faculty Fellow at Booth, having joined the faculty in 2017. Liang earned a PhD in statistics from the Wharton School at the University of Pennsylvania in 2017 and a BSc in mathematics and applied mathematics from Peking University in 2012. Liang's research has appeared in journals such as Econometrica, The Annals of Statistics, the Journal of the American Statistical Association, the Journal of the Royal Statistical Society, and the Journal of Machine Learning Research, as well as in leading peer-reviewed machine learning venues. He is currently on the Editorial Board of the Journal of Machine Learning Research and the Senior Program Committee for the Conference on Learning Theory.
Liang’s recent work has focused on learning theory, mathematical statistics, and stochastic optimization. In the Autumn Quarter of 2020, he taught Business Statistics and led the Econometrics and Statistics Colloquium at Booth.
The Federal Reserve is poised to take action in the United States, but that’s just one step on the road to post-pandemic recovery, experts shared at Economic Outlook 2022 in Hong Kong.
Charting a Course Back to Normal
The Duality program will leverage the region’s quantum ecosystem to help startups bring their innovations to the marketplace.
Nation’s First Quantum Startup Accelerator Launches at UChicago
The latest issue of Chicago Booth Review covers how this recession differs from past ones and why public policy has largely failed to instill confidence in Americans
COVID-19 Thought Leadership Digest: September 2
Stay informed with Booth's newsletter, event notifications, and regular updates featuring faculty research and stories of leadership and impact.
YOUR PRIVACY
We want to demonstrate our commitment to your privacy. Please review Chicago Booth's privacy notice, which provides information explaining how and why we collect particular information when you visit our website.
