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 arXiv, 2023
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 Journal of Computational and Applied Mathematics, 2022
Analysis of eigenvalue methods for multivariate numerical rootfinding.