Research Overview

My primary research interests lie in machine learning, particularly at the intersection of applied probability, dynamical systems, and modern neural networks. While my work focuses on leveraging foundational questions to advance the science and engineering of learning systems, the theory is closely connected to implementation challenges and a broad spectrum of practical applications across the sciences.

Some central themes of interest:

• Generative modeling: how to improve existing generative modeling methods, particularly for learning sequential data
• Sequence modeling: how to use ML to model and learn sequential data, particularly those with underlying non-trivial dynamics
• Robustness: how to leverage randomness to make ML safer and more reliable
• Optimization and sampling: how to understand and improve optimization and sampling algorithms in ML meaningfully

I also have a long-standing interest in multiscale stochastic dynamics, especially homogenization and related applications in statistical mechanics, including both classical mathematical approaches and emerging data-driven methods.