Jiwei Zhao, PhD
Home
 |
Jiwei Zhao
Associate Professor
Affiliated Faculty
E-mail: jiwei DOT zhao AT wisc DOT edu; jiwei2012zhao AT gmail DOT com |
Research Interests
Jiwei Zhao's research focuses on applying semiparametric techniques to understand the complex structure of modern biomedical data sets, usually in the pursuit of efficiency, robustness, and the tradeoff between the two. Specifically, his work has concentrated in the fields of:
distribution shift, domain adaptation and transfer learning,
weakly supervised machine learning (semi-supervised, label noise, etc.),
missing data analysis and causal inference,
high-dimensional statistical inference.
Together with Dr. David Francis, Jiwei co-leads the NIH R01 project NIH/NIDCD/R01DC021431 (2023-2028) entitled CoPE II: Individualizing Patient-Reported Outcomes in Patient Care for Vocal Fold Paralysis in the Clinic and in Research. Currently patients are being recruited across a 37-site national collaborative of high-volume voice centers.
Jiwei's research is also supported by the NSF through the DMS/NIGMS program under award numbers 1953526 and 2122074 and the Statistics program under award number 2310942 , as well as by the Data Science Institute of UW-Madison.
Short Bio
Jiwei Zhao is currently an Associate Professor at the University of Wisconsin-Madison, jointly appointed by the Departments of Statistics & of Biostatistics and Medical Informatics. He obtained his Bachelor’s degree in Mathematics (Chern Honored Class) from Nankai University, and earned his PhD in Statistics from UW-Madison in 2012 under the supervision of Dr. Jun Shao. Before returning to Madison in 2020, he was a Postdoctoral Researcher at Yale University (2012-2013) under the mentorship of Dr. Heping Zhang, and Assistant then Associate Professor at the State University of New York at Buffalo (2014-2020), in the United States.
His research interests include semiparametric statistics, the tradeoff between efficiency and robustness, domain adaptation and transfer learning, missing data analysis and causal inference, high-dimensional statistical inference. His applied research focuses on patient-reported outcomes, clinical trials, real-world evidence and real-world data, electronic health records (EHR), survey data, health disparity, mental health, drug abuse, and cancer. His work has been published in top-tier statistical journals as well as in leading machine learning conferences. His research has been consistently supported by the US National Science Foundation and the National Institutes of Health.
Jiwei is now Associate Editor for Annals of Applied Statistics, JRSS Series A: Statistics in Society, Scandinavian Journal of Statistics and Journal of Nonparametric Statistics. He is also Area Chair for the annual International Conference on Artificial Intelligence and Statistics (AISTATS) in 2024, 2025.
Recent News and Activities
The group is consistently looking for self-motivated researchers (postdocs [position.pdf], PhD students, Master students, and undergrads) with strong statistical/computational skills to join us. For prospective PhD students, please consider applying Statistics PhD program with Statistics option, or Statistics PhD program with Biostatistics option, both administered by the Department of Statistics, or Biomedical Data Science PhD program administered by the Department of Biostatistics and Medical Informatics.
More to be added soon!
[1/14/2025] UW-Madison is implementing a new Distinguished Research Fellows Program for postdocs. If you are interested, please email me.
Together with Dr. Chris Holmes of Oxford and Dr. Beth Tipton of Northwestern, Jiwei will co-organize the workshop New Horizons on Model Transportability and Data Integration in June 2026 at the IMSI of Chicago!
Jiwei serves as the Program Chair-Elect (2025) and Program Chair (2026) for the Statistical Learning and Data Science section of the ASA.
At the 2025 JSM, Jiwei will teach a CE (Continuing Education) course entitled Disentangle the Semiparametric Structure in Statistical Models, with Applications in Causal Inference and Model Transportability. More details will be coming out soon.
