Search Results for author: George Edward Dahl

Found 1 papers, 0 papers with code

A Loss Curvature Perspective on Training Instabilities of Deep Learning Models

no code implementations ICLR 2022 Justin Gilmer, Behrooz Ghorbani, Ankush Garg, Sneha Kudugunta, Behnam Neyshabur, David Cardoze, George Edward Dahl, Zachary Nado, Orhan Firat

In this work, we study the evolution of the loss Hessian across many classification tasks in order to understand the effect the curvature of the loss has on the training dynamics.

Navigate

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