My research focuses on the theoretical and algorithmic aspects of data science and machine learning, motivated by the challenge of extracting useful information from large-scale and high-dimensional data, particularly in sample-starved or resource-starved environments. I am interested in exploiting and developing low-dimensional data representations that reveal geometric structures to reduce the sampling cost of information acquisition and improve the performance of decision making. Using tools in signal processing, high-dimensional statistics, optimization, sampling and information theory, we develop provably efficient algorithms, both statistically and computationally, for applications in sensing systems, imaging science, and biomedical domains.

Here is a video that highlights some of our research.

Research Support

I gratefully acknowledge ongoing and past support from NSF (e.g., CCF-2007911, CCF-1901199, CCF-1806154, CAREER ECCS-1650449), AFOSR (YIP), ONR (YIP, PECASE), NIH (R01), ARO, AFRL (COE), Center for Surveillance Research, ORAU, Simons Foundation, Google and Microsoft for my research group.