Our vision is to formulate and solve fundamental problems arising in learning systems. These problems are motivated by the needs for safety, robustness and fairness of learning algorithms in applications ranging from healthcare, robotics and transportation to economics and public policy.
We approach engineering and societal problems brought to our attention from industry or applied sectors by focusing on their mathematical underpinnings. We find that abstracting the problems to their core challenges is the first step to gaining the clarity needed to solve them. Bringing together insights, techniques, and expertise from optimization, statistics, learning, signal-processing and control, we develop theoretical frameworks and algorithmic solutions. We verify and apply our findings through partnerships with industry, healthcare and government.
| Name | Research Interests |
|---|---|
| Renjie Liao | Machine Learning, Deep Learning, Statistical Learning Theory, Computer Vision, Machine Learning for Programming Languages, Natural Language Processing, Self-Driving |
| Dominic Liao-McPherson | Predictive and Constrained Control, Multi-agent Systems, Algorithmic Game Theory, Real-time Embedded and Distributed Optimization, Energy Systems, Aerospace, Robotics. |
| Alberto Padoan | Optimization, Learning, Control, Mathematical Biology, Cyber-Physical Systems, Traffic Networks |
| Christos Thrampoulidis | High-dimensional signal processing, machine learning, optimization, statistics, mathematical data science |
| Lele Wang | Information theory, coding theory, communication theory, mathematical data science |
| Xiaoxiao Li | Machine Learning, Deep Learning, Explainable AI, Trustworthy AI, Privacy and Security, Medical Image Analysis, Bioinformatics |