
My research group conducts research in the following areas of statistics and machine learning:
- deep learning and deep generative models
- methods and scalable algorithms for high-dimensional data
- Bayesian methodology and computation
- matrix completion and recommender systems
- survival analysis and causal inference
Prospective Students
My group is looking for highly motivated students to work in one or more of the following areas: deep learning, Bayesian inference, causal inference, and scalable algorithms for big data. To work with me, you must be currently enrolled as a student at USC. PhD students interested in my supervision must also first pass the PhD Qualifying Exam (offered every August). Information for prospective studentsRecent News
- January 2025: My student Zile Zhao has defended his PhD dissertation “Methods and Applications for Bayesian Semiparametric Survival Analysis” and will join the Moffitt Cancer Center as a postdoctoral fellow. Congratulations, Zile!
- January 2025: “Two-step mixed-type multivariate Bayesian sparse variable selection with shrinkage priors” (with Shao-Hsuan Wang and Hsin-Hsiung Huang) has been published in Electronic Journal of Statistics. Paper
- November 2024: “Generative quantile regression with variability penalty” (with Shijie Wang and Minsuk Shin) has been published in Journal of Computational and Graphical Statistics. Paper
- November 2024: “A unified three-state model framework for analysis of treatment crossover in survival trials” (with Zile Zhao, Ye Li, and Xiaodong Luo) has been accepted by Statistics in Biopharmaceutical Research. Paper
- November 2024: “Bayesian modal regression based on mixture distributions” (with Qingyang Liu and Xianzheng Huang) has been published in Computational Statistics & Data Analysis. Paper
- September 2024: “VCBART: Bayesian trees for varying coefficients” (with Sameer Deshpande, Cecilia Balocchi, Jennifer Starling, and Jordan Weiss) has been accepted by Bayesian Analysis. Paper
- August 2024: My former PhD student Shijie Wang (PhD ’24) has had the first chapter of his dissertation “Generative multi-purpose sampler for weighted M-estimation” (co-authored with Minsuk Shin and Jun Liu) published in Journal of Computational and Graphical Statistics. Paper
- June 2024: New preprint “Neural-g: A deep learning framework for mixing density estimation” (with Shijie Wang, Saptarshi Chakraborty, and Qian Qin). arXiv
- May 2024: My student Shijie Wang has defended his PhD dissertation “New Deep Learning Approaches to Classical Statistical Problems” and will join Gauss Labs as an Applied Scientist. Congratulations, Shijie!
- March 2024: “Fast bootstrapping nonparametric maximum likelihood for latent mixture models” (with Shijie Wang and Minsuk Shin) has been published in IEEE Signal Processing Letters. Paper