Published in PLOS Computational Biology, 2025
Highlights principles of effective strategies for trainee-led computational biology educational outreach.
Published in SIAM Journal on Mathematics of Data Science, 2025
Connects the representation cost of neural networks with 1 ReLU layer and many linear layers to the spectrum of the expected gradient outer product matrix (EGOP), showing that this architecture is biased towards single- and multi-index models.
Published in arXiv Preprint, 2025
Analyzes how deep linear neural networks trained via gradient descent with weight decay automatially adapt to structure in data from inverse problems.
Published in 37th Annual Conference on Learning Theory (COLT), 2024
Establishes a separation in the representation cost and sample complexity needed to approximate functions with two vs. three layer neural networks.
Published in Journal of Computational and Applied Mathematics, 2022
Analysis of eigenvalue methods for multivariate numerical rootfinding.