About me
I am a fifth year Ph.D. candidate in the Division of Computational and Data Sciences at Washington University in St. Louis. I’m honored to be advised by Prof. Roman Garnett in the Department of Computer Science & Engineering and Prof. Jacob Montgomery in the Department of Political Science. Previously, I received my B.S. in Computer Science at University of Michigan in 2019. I also earned a B.S.E. in Electrical & Computer Engineering at Shanghai Jiao Tong University in 2019, under the UM-SJTU Joint Institute.
You can find my CV here.
News
- [New]Sept, 2023: “A Gaussian Process Framework for Social Science Models” appeared on Better Models, Better Predictions panel in APSA 2023.
- AUG, 2023: “A Dynamic, Ordinal Gaussian Process Item Response Theoretic Model” appeared on Political Scaling panel in the Annual Meeting of APSA 2023.
- Jul, 2023: “Generalized budget-constrained conjoint analysis via active learning” was presented at PolMeth XL as a poster.
- May, 2023: I presented “Active learning for marginal effect estimation in Gaussian Process preference learning” at the 9th Information and Statistics for Nuclear Experiment and Theory workshop as a poster.
- Apr, 2023: I successfully proposed my Ph.D. dissertation, Advancing Modeling and Inference in Political Science with Gaussian Processes.
- Jan, 2023: “A Multi-Task Gaussian Process Model for Inferring Time-Varying Treatment Effects in Panel Data” was accepted to AISTATS 2023.
- Jul, 2022: A poster was accepted in the annual Summer Meeting of Society for Political Methodology (2022).
- Jan 2021: “Polls, Context, and Time: A Dynamic Hierarchical Bayesian Forecasting Model for US Senate Elections” was published in Political Analysis.
- Aug 2020: “Compressive Big Data Analytics: An ensemble meta-algorithm for high-dimensional multisource datasets” was published in PLOS ONE.
Research Interests
My research interests lie in the intersection of Bayesian machine learning and quantitative methods. My work spans causal inference, psychometrics, optimal treatment design and election forecasting, contributing to a richer understanding of political behavior and outcomes. My dissertation thesis focuses on advancing modeling and inference in Political Science with Gaussian Processes to address complex challenges in the field. I particularly study heterogeneous treatmenet effect estimation from longitudinal data, non-parametric item response theory for political measurement, adaptive experimentation for virtual experiments and election forecasting.