Research
I'm broadly interested in machine learning theory, in particular the design and analysis of statistically and computationally efficient algorithms. I'm especially interested in the simplest such algorithms, and learning in structured settings.
I work on statistical learning theory with Nikita Zhivotovskiy in Berkeley's Statistical Machine Learning group, and on deep learning theory with Michael DeWeese at BAIR. I also work on computational nuclear physics at LLNL.
[Google Scholar] / [ORCID] / [TLDRs]
Publications
Majority-of-Three is Optimal
Preprint. Under review. [arXiv]
A Theory of Saddle Escape in Deep Nonlinear Networks
Preprint. Under review. [arXiv]
Rao-Blackwellized Score Matching on Manifolds
ICML 2026, Workshop on Structured Probabilistic Inference and Generative Modeling. [arXiv]
ALPHANSO: Open-Source Modeling of (\(\alpha\),n) Neutron Source Terms
Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment. [doi] / [code]
Short version at the American Nuclear Society Student Conference, 2026. Best Paper in Mathematics, Computation, and AI Applications.
Short version at the Institute of Nuclear Materials Management Annual Meeting, 2026.
Invited talks at LBNL, LLNL, UT Knoxville.