2024
Stepping on the Edge: Curvature Aware Learning Rate Tuners
Vincent Roulet, Atish Agarwala, Jean-Bastien Grill, Grzegorz Michal Swirszcz, Mathieu Blondel, Fabian Pedregosa
NeurIPS 2024poster
Curvature information -- particularly, the largest eigenvalue of the loss Hessian, known as the sharpness -- often forms the basis for learning rate tuners. However, recent work has shown that the curvature information undergoes complex dynamics during training, going from a phase of increasing shar…