Overview
I develop statistical and machine learning methods for high- or infinite-dimensional problems from applied and computational mathematics. My work blends operator learning with ideas from inverse problems, generative modeling, and uncertainty quantification. A current focus of my research involves working in the space of probability measures.
Research Focus
Machine learning, inverse problems, scientific computing
Publications
- Operator learning using random features: a tool for scientific computing (with A.M. Stuart), SIAM Review Vol. 66 No. 3 (2024) pp. 535-571
- An operator learning perspective on parameter-to-observable maps (with D.Z Huang and M. Trautner), Foundations of Data Science Vol. 7 No. 1 (2025) pp. 163-225
- Convergence rates for learning linear operators from noisy data (with M.V. De Hoop, N.B. Kovachki, and A.M. Stuart), SIAM/ASA J. Uncertainty Quantification Vol. 11 No. 2 (2023) pp. 480-513
- Error bounds for learning with vector-valued random features (with S. Lanthaler), Advances in Neural Information Processing Systems Vol. 36 (2023) pp. 71834-71861