LGRT 1423J

My research is centered on the mathematical underpinnings of data science and machine learning (ML). One of my primary objectives is to address the critical challenge of quantifying and enhancing the robustness and statistical efficiency of ML models, especially for data-scarce and resource-constrained applications. I am interested in understanding and leveraging the inherent geometric structures of the underlying systems, aiming to develop efficient ML models and computational algorithms and provide theoretical guarantees on their performance. My research draws from a diverse array of mathematical disciplines, including applied harmonic analysis, differential geometry, applied probability, PDE, and optimization. Much of my research is driven by a range of scientific and interdisciplinary applications, spanning domains from scientific computing, reduced order modeling, computer vision, to entomology and public health.


Ph.D. Applied Mathematics, University of California Los Angeles, 2017

B.S. Mathematics, Tsinghua University, 2012


Mathematical theory of data science and machine learning; statistical learning theory; optimization; applied harmonic analysis; applied probability; scientific computing; PDE and dynamical systems; computer vision and image processing