L4: Practical loss-based stepsize adaptation for deep learning

We propose a stepsize adaptation scheme for stochastic gradient descent. It operates directly with the loss function and rescales the gradient in order to make fixed predicted progress on the loss. We demonstrate its capabilities by conclusively improving the performance of Adam and Momentum optimiz...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Rolinek, Michal, Martius, Georg
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 30.11.2018
Subjects
Adaptation
Deep learning
Online AccessGet full text

Cover

More Information
Summary:We propose a stepsize adaptation scheme for stochastic gradient descent. It operates directly with the loss function and rescales the gradient in order to make fixed predicted progress on the loss. We demonstrate its capabilities by conclusively improving the performance of Adam and Momentum optimizers. The enhanced optimizers with default hyperparameters consistently outperform their constant stepsize counterparts, even the best ones, without a measurable increase in computational cost. The performance is validated on multiple architectures including dense nets, CNNs, ResNets, and the recurrent Differential Neural Computer on classical datasets MNIST, fashion MNIST, CIFAR10 and others.
ISSN:2331-8422