How does batch normalization help optimization?
Name
7515-how-does-batch-normalization-help-optimization.pdf
Description
Published version
Size
1.69 MB
Format
Adobe PDF
Checksum (MD5)
bb972419690359597e95c3ef97ffe57b
Author(s)
Madry, Aleksander
Santurkar, Shibani
Tsipras, Dimitris
Ilyas, Andrew
Date Issued
2018
Citation
Madry, Aleksander, Santurkar, Shibani, Tsipras, Dimitris and Ilyas, Andrew. 2018. "How does batch normalization help optimization?."
Version
Final published version
Abstract
© 2018 Curran Associates Inc.All rights reserved. Batch Normalization (BatchNorm) is a widely adopted technique that enables faster and more stable training of deep neural networks (DNNs). Despite its pervasiveness, the exact reasons for BatchNorm's effectiveness are still poorly understood. The popular belief is that this effectiveness stems from controlling the change of the layers' input distributions during training to reduce the so-called “internal covariate shift”. In this work, we demonstrate that such distributional stability of layer inputs has little to do with the success of BatchNorm. Instead, we uncover a more fundamental impact of BatchNorm on the training process: it makes the optimization landscape significantly smoother. This smoothness induces a more predictive and stable behavior of the gradients, allowing for faster training.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://papers.nips.cc/paper/7515-how-does-batch-normalization-help-optimization
