Norm matters: efficient and accurate normalization schemes in deep networks
Abstract
Over the past few years, Batch-Normalization has been commonly used in deep networks, allowing faster training and high performance for a wide variety of applications. However, the reasons behind its merits remained unanswered, with several shortcomings that hindered its use for certain tasks. In this work, we present a novel view on the purpose and function of normalization methods and weight-decay, as tools to decouple weights' norm from the underlying optimized objective. This property highlights the connection between practices such as normalization, weight decay and learning-rate adjustments. We suggest several alternatives to the widely used batch-norm, using normalization in and spaces that can substantially improve numerical stability in low-precision implementations as well as provide computational and memory benefits. We demonstrate that such methods enable the first batch-norm alternative to work for half-precision implementations. Finally, we suggest a modification to weight-normalization, which improves its performance on large-scale tasks.
Cite
@article{arxiv.1803.01814,
title = {Norm matters: efficient and accurate normalization schemes in deep networks},
author = {Elad Hoffer and Ron Banner and Itay Golan and Daniel Soudry},
journal= {arXiv preprint arXiv:1803.01814},
year = {2019}
}
Comments
http://papers.nips.cc/paper/7485-norm-matters-efficient-and-accurate-normalization-schemes-in-deep-networks