# Benjamin Zhang

Postdoctoral Research Associate

I am teaching MATH 590STA: Introduction to Mathematical Machine Learning in Spring 2024. Check out the course website!

I am a postdoctoral research associate in the Department of Mathematics and Statistics at UMass Amherst working with Markos Katsoulakis, Luc Rey-Bellet, and Paul Dupuis. My research lies at the intersection of computational statistics and computational dynamics. I enjoy studying how these two fields interact with and complement each other for predictive modeling and uncertainty quantification.

My current research interests include mathematics of generative modeling, rare event simulation for dynamical systems, and sampling methods for Bayesian computation.

##
Education

Ph.D. Computational Science & Engineering, MIT, 2022

S.M. Aeronautics & Astronautics, MIT, 2017

B.S. Engineering Physics, UC Berkeley, 2015

B.A. Applied Mathematics, UC Berkeley, 2015

##
RESEARCH INTERESTS

Mathematics of data science, Generative Modeling, Bayesian computation, Rare event simulation

##
Selected Publications

- Zhang, B. J., Liu, S., Li, W., Katsoulakis, M. A., Osher, S. (2024). Wasserstein proximal operators describe score-based generative models and resolve memorization.
*Preprint.* - Zhang, B. J., & Katsoulakis, M. A. (2023). A mean-field games laboratory for generative modeling.
*Preprint.* - Zhang, B. J., Marzouk Y. M., and Spiliopoulos, K. (2023). "Transport map unadjusted Langevin algorithms.
*Preprint.* - Zhang, B. J., Sahai, T., & Marzouk, Y. M. (2022). A Koopman framework for rare event simulation in stochastic differential equations.
**Journal of Computational Physics.** - Zhang, B. J., Marzouk, Y. M., & Spiliopoulos, K. (2022). Geometry-informed irreversible perturbations for accelerated convergence of Langevin dynamics.
**Statistics and Computing**