Didong Li, PhD

About

Dr. Didong Li is an assistant professor in the Department of Biostatistics at UNC-Chapel Hill. 

His research focus is statistical methods development for robust inference of complex and high-dimensional data, specifically covering manifold learning, nonparametric Bayesian inference, information geometry, and spatial statistics. He has applied these methods to electronic healthcare record data, large-scale genetic and survey data, and single-cell RNA-sequencing data.

Honors and Awards

Inaugural IMS Lawrence D. Brown PhD Student Award
2019, Institute of Mathematical Statistics

Research Activities

Research Interests

Dimension reduction

Gaussian process

Geometric data analysis

Information geometry

Nonparametric Bayes

Spatial statistics

Service Activities

Meeting/Session Organizer:

JSM Invited Session, “Geometry & Bayes: Better Together” (2021)

JSM Invited Session, “Gaussian Process Models over non-Euclidean Domains” (2022)

Editorial Board: Journal of Machine Learning Research

Referee for:

Annals of Applied Statistics

Annals of Statistics

Conference on Neural Information Processing Systems (NeurIPS)

Electronic Journal of Statistics

IEEE Transactions on Neural Networks and Learning Systems

International Conference on Artificial Intelligence and Statistics (AISTATS)

Journal of the American Statistical Association

Journal of Computational and Graphical Statistics

Statistica Sinica

Key Publications

Efficient manifold approximation with spherelets. D. Li, M. Mukhopadhyay and DB. Dunson (2022). Journal of Royal Statistical Society: Series B.

Classification via local manifold approximation. D. Li and DB. Dunson (2020). Biometrika.

Estimating densities with nonlinear support using Fisher-Gaussian kernels.  M. Mukhopadhyay, D. Li and DB. Dunson (2020). Journal of Royal Statistical Society: Series B.

Education