Published multiple papers including 'The Within-Orbit Adaptive Leapfrog No-U-Turn Sampler' (2025), 'Antithetic Noise in Diffusion Models' (2025), 'Flexible Selective Inference with Flow-based Transport Maps' (2025), etc. 'Selective Inference with Distributed Data' published in the Journal of Machine Learning Research, 'Conditional Quasi-Monte Carlo with Constrained Active Subspaces' in SIAM Journal on Scientific Computing, and 'Langevin Quasi-Monte Carlo' in NeurIPS 2024.
Research Experience
Research Scientist at the Center for Computational Mathematics at the Flatiron Institute (2024–2025).
Education
Ph.D. in Statistics from Stanford University in 2024; B.S. in Mathematics from Tsinghua University in 2019.
Background
Assistant Professor in the Department of Statistical Science at Duke University. Research focuses on statistical and computational methods, with a focus on the adaptive nature of modeling and analysis in modern data science. Particularly interested in sampling algorithms with applications to Bayesian inference, selective inference, and generative modeling.
Miscellany
Co-organizes an online seminar on Monte Carlo methods.