pith. machine review for the scientific record. sign in

arxiv: 1803.01814 · v3 · pith:FOVFFVOXnew · submitted 2018-03-05 · 📊 stat.ML · cs.LG

Norm matters: efficient and accurate normalization schemes in deep networks

classification 📊 stat.ML cs.LG
keywords normalizationbatch-normdeepimplementationsmethodsnetworksnormperformance
0
0 comments X
read the original 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 $L^2$ batch-norm, using normalization in $L^1$ and $L^\infty$ 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Root Mean Square Layer Normalization

    cs.LG 2019-10 conditional novelty 5.0

    RMSNorm delivers re-scaling invariance and comparable accuracy to LayerNorm while cutting computation by skipping mean subtraction, yielding 7-64% runtime reductions across tested models.