- CCS: Controllable and Constrained Sampling with Diffusion Models via Initial Noise Perturbation
- Quantum speedup of non-linear Monte Carlo problems
- On importance sampling and independent Metropolis-Hastings with an unbounded weight function
- Spectral gap bounds for reversible hybrid Gibbs chains
- Repeated averages on graphs
- A phase transition in sampling from Restricted Boltzmann Machines
- Connecting Quantum Computing with Classical Stochastic Simulation
- Differentially Private Range Queries with Correlated Input Perturbation
Awards and Grants:
- NSF DMS-2210849
- NSF FET-2403007
- Adobe Data Science Research Award
Research Experience
Currently an Assistant Professor in the Department of Statistics at Rutgers University, New Brunswick. Organizes a weekly online seminar on Monte Carlo methods.
Education
B.S. in Mathematics from the University of Science and Technology of China (USTC) in June 2015; Ph.D. in Mathematics (Ph.D. minor in Statistics) from Stanford University in August 2020, advised by Prof. Persi Diaconis.
Background
Research interests include Monte Carlo methods, generative AI, quantum computing, and probability. Encourages students with a strong programming background to get in touch.