My primary research interests are in mathematical and physics-inspired machine learning, particularly topics at the interface of random dynamical systems and modern neural networks. While there is a focus on using foundational/theoretical questions to drive advances in the science and engineering of learning systems, the theory is strongly tied to implementational problems and a wide range of very practical applications.
Some central themes of interest:
- Randomness in/of/for robust and reliable machine learning
- Implicit regularization and optimization in machine learning
- Machine learning through the lens of dynamical systems and statistical mechanics