1.2k citations · 1.3k across the 27 of their papers we have counts for
6 papers · 1 filter
When, why, and how do diffusion posterior samplers fail? A finite-sample lens
Benjamin A. Burns, Sara Fridovich-Keil
Diffusion models have excellent capacity to model complex distributions of natural data, which has made them a popular and effective choice for posterior sampling in imaging invers…
A Recovery Guarantee for Sparse Neural Networks
Sara Fridovich-Keil, Mert Pilanci
We prove the first guarantees of sparse recovery for ReLU neural networks, where the sparse network weights constitute the signal to be recovered. Specifically, we study structural…
Solving Inverse Problems in Protein Space Using Diffusion-Based Priors
Axel Levy, Eric R. Chan, Sara Fridovich-Keil +3
The interaction of a protein with its environment can be understood and controlled via its 3D structure. Experimental methods for protein structure determination, such as X-ray cry…
Models Out of Line: A Fourier Lens on Distribution Shift Robustness
Sara Fridovich-Keil, Brian R. Bartoldson, James Diffenderfer +2
Improving the accuracy of deep neural networks (DNNs) on out-of-distribution (OOD) data is critical to an acceptance of deep learning (DL) in real world applications. It has been o…
Spectral Bias in Practice: The Role of Function Frequency in Generalization
Sara Fridovich-Keil, Raphael Gontijo-Lopes, Rebecca Roelofs
Despite their ability to represent highly expressive functions, deep learning models seem to find simple solutions that generalize surprisingly well. Spectral bias -- the tendency…
Neural Kernels Without Tangents
Vaishaal Shankar, Alex Fang, Wenshuo Guo +4
We investigate the connections between neural networks and simple building blocks in kernel space. In particular, using well established feature space tools such as direct sum, ave…