Search Results for author: Jeremy M. Cohen

Found 1 papers, 1 papers with code

Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability

1 code implementation ICLR 2021 Jeremy M. Cohen, Simran Kaur, Yuanzhi Li, J. Zico Kolter, Ameet Talwalkar

We empirically demonstrate that full-batch gradient descent on neural network training objectives typically operates in a regime we call the Edge of Stability.

Cannot find the paper you are looking for? You can Submit a new open access paper.