Wanrong Zhu

Wanrong Zhu is broadly interested in statistical inference problems, with her research situated at the intersection of statistics, machine learning and stochastic optimization. Her recent work focuses on the theory and methods of uncertainty quantification for machine learning in modern settings, such as those involving Stochastic Gradient Descent or distribution-free inference methods. Additionally, she is interested in goodness-of-fit testing, algorithmic stability, data privacy and adaptive data analysis.

Education

Ph.D., Statistics, University of Chicago