harvard art museums

Divit Rawal

I'm an undergrad at Berkeley studying statistics, computer science, and physics.

I'm interested in learning theory and high-dimensional statistics. I work on statistical learning theory in Berkeley's StatML group with Nikita Zhivotovskiy and deep learning theory at BAIR with Michael DeWeese.

Selected Publications

Majority-of-Three is Optimal

with N. Zhivotovskiy. Under review. [arXiv]

A Theory of Saddle Escape in Deep Nonlinear Networks

with M. R. DeWeese. Under review. [arXiv]

Rao-Blackwellized Score Matching on Manifolds

ICML 2026, Workshop on Structured Probabilistic Inference and Generative Modeling. [arXiv]