DeepAI AI Chat
Log In Sign Up

Quasi-hyperbolic momentum and Adam for deep learning

by   Jerry Ma, et al.

Momentum-based acceleration of stochastic gradient descent (SGD) is widely used in deep learning. We propose the quasi-hyperbolic momentum algorithm (QHM) as an extremely simple alteration of momentum SGD, averaging a plain SGD step with a momentum step. We describe numerous connections to and identities with other algorithms, and we characterize the set of two-state optimization algorithms that QHM can recover. Finally, we propose a QH variant of Adam called QHAdam, and we empirically demonstrate that our algorithms lead to significantly improved training in a variety of settings, including a new state-of-the-art result on WMT16 EN-DE. We hope that these empirical results, combined with the conceptual and practical simplicity of QHM and QHAdam, will spur interest from both practitioners and researchers. PyTorch code is immediately available.


page 1

page 2

page 3

page 4


Stochastic Normalized Gradient Descent with Momentum for Large Batch Training

Stochastic gradient descent (SGD) and its variants have been the dominat...

Momentum Doesn't Change the Implicit Bias

The momentum acceleration technique is widely adopted in many optimizati...

Towards understanding how momentum improves generalization in deep learning

Stochastic gradient descent (SGD) with momentum is widely used for train...

Accelerate Distributed Stochastic Descent for Nonconvex Optimization with Momentum

Momentum method has been used extensively in optimizers for deep learnin...

Asynchrony begets Momentum, with an Application to Deep Learning

Asynchronous methods are widely used in deep learning, but have limited ...

On Uniform Boundedness Properties of SGD and its Momentum Variants

A theoretical, and potentially also practical, problem with stochastic g...

Variance Reduction in Deep Learning: More Momentum is All You Need

Variance reduction (VR) techniques have contributed significantly to acc...