Tian Li

I am an Assistant Professor at the Computer Science Department and the Data Science Institute at the University of Chicago. I am also a member of the UChicago Committee on Computational and Applied Mathematics.

My research centers around large-scale machine learning and optimization.

My group is interested in the tradeoffs between model utilities/convergence and systems efficiency (e.g., in terms of memory, compute, and communication costs), particularly in large-scale settings (e.g., large generative models). We improve such tradeoffs by designing cheaper optimizers, exploring new distributed training algorithms, and making better use of data from different distributions.

We are also interested in other critical aspects of machine learning training and deployment beyond accuracy and efficiency, such as privacy and robustness. We propose varying definitions that tailor practical applications, study the interconnections between (various measurements of) privacy, robustness, generalization, memorization, and reasoning, and design provable algorithms to solve the objectives at scale.

I am always looking for strong and motivated undergraduate and graduate students and postdocs. For Ph.D. applicants, please apply through the CS PhD program and/or the DS PhD program, and mention my name in your application(s).