I am currently a postdoctoral researcher in the Department of Statistics at the University of California, Davis, working with Professors Hans-Georg Müller and Jane-Ling Wang. I earned my Ph.D. in Statistics from Peking University in 2022, under the supervision of Professor Fang Yao.

My research spans methodology, theory and application in statistics. During my Ph.D. at Peking University, I focused on optimal convergence and phase transitions in discretely observed functional data, particularly those involving inverse problems. We developed a unified theory for the optimal convergence rates and phase transitions for a diverging number of eigenfunctions, addressing an open problem important for subsequent analyses.

My current research interests includes:

Theory and methodology for:

• Statistical modeling and inference for object data, including but not limited to distributions, trees, and compositional data
• Functional data with complex structure, including discretely observed and non-Euclidean data
• Learning theory, generalization bound for deep neural network
• Model agnostic method and its applications in real-world dataset, e.g., anomalies detection

Application areas:

• Longitudinal/Compositional data in biological and medical sciences
• Brain image data (MRI, fMRI)

Contact

• Office: 4229 Mathematical Science Building, University of California, Davis, CA 95616
• Email: hgzhou[at]ucdavis[dot]edu