activity
20182025
most citedA Loss Curvature Perspective on Training Instability in Deep Learning

6 citations · 10 across the 3 of their papers we have counts for

collaborators
Showing cs.LGShow all

12 papers · 1 filter

cs.LG20252 cited

Accelerating Neural Network Training: An Analysis of the AlgoPerf Competition

Priya Kasimbeg, Frank Schneider, Runa Eschenhagen +11

The goal of the AlgoPerf: Training Algorithms competition is to evaluate practical speed-ups in neural network training achieved solely by improving the underlying training algorit…

cs.LG20222 cited

AI system for fetal ultrasound in low-resource settings

Ryan G. Gomes, Bellington Vwalika, Chace Lee +26

Despite considerable progress in maternal healthcare, maternal and perinatal deaths remain high in low-to-middle income countries. Fetal ultrasound is an important component of ant…

cs.LG20216 cited

A Loss Curvature Perspective on Training Instability in Deep Learning

Justin Gilmer, Behrooz Ghorbani, Ankush Garg +6

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.…

cs.LG2021

A Large Batch Optimizer Reality Check: Traditional, Generic Optimizers Suffice Across Batch Sizes

Zachary Nado, Justin M. Gilmer, Christopher J. Shallue +2

Recently the LARS and LAMB optimizers have been proposed for training neural networks faster using large batch sizes. LARS and LAMB add layer-wise normalization to the update rules…

cs.LG2019

On Empirical Comparisons of Optimizers for Deep Learning

Dami Choi, Christopher J. Shallue, Zachary Nado +3

Selecting an optimizer is a central step in the contemporary deep learning pipeline. In this paper, we demonstrate the sensitivity of optimizer comparisons to the hyperparameter tu…

cs.LG2019

Faster Neural Network Training with Data Echoing

Dami Choi, Alexandre Passos, Christopher J. Shallue +1

In the twilight of Moore's law, GPUs and other specialized hardware accelerators have dramatically sped up neural network training. However, earlier stages of the training pipeline…