My research develops statistical methodology for reliable inference and uncertainty quantification in complex biomedical data, where distribution shift, outcome heterogeneity, and imperfect measurements are unavoidable. I focus on methods that are robust, interpretable, and computationally scalable, motivated by problems in statistical genetics and genomics, epidemiology, and electronic health records.

My current research program is organized around two main methodological themes, together with a bridging line of work on scalable inference for biobank-scale studies. Selected papers are listed below. For a complete and up-to-date list of publications, please refer to the Publications page.

underline indicates a student co-author under my (co)supervision, with ♦ denoting an undergraduate student mentee; ✉ indicates the corresponding author.

Distribution shift, robust learning, and uncertainty quantification

Quantile-based modeling and heterogeneity in statistical genetics

Bridge: Scalable inference for biobank-scale association studies

This line of work develops general-purpose, scalable inference tools for large biobank studies. These papers complement my two main themes by providing robust and computationally efficient building blocks for association analysis at population scale.