CDF Normalization for Controlling the Distribution of Hidden Nodes

Mike Van Ness, Madeleine Udell
Proceedings on "I (Still) Can't Believe It's Not Better!" at NeurIPS 2021 Workshops, PMLR 163:64-68, 2022.

Abstract

Batch Normalizaiton (BN) is a normalization method for deep neural networks that has been shown to accelerate training. While the effectiveness of BN is undisputed, the explanation of its effectiveness is still being studied. The original BN paper attributes the success of BN to reducing internal covariate shift, so we take this a step further and explicitly enforce a Gaussian distribution on hidden layer activations. This approach proves to be ineffective, demonstrating further that reducing internal covariate shift is not important for successful layer normalization.

Cite this Paper


BibTeX
@InProceedings{pmlr-v163-ness22a, title = {{CDF} Normalization for Controlling the Distribution of Hidden Nodes}, author = {Ness, Mike Van and Udell, Madeleine}, booktitle = {Proceedings on "I (Still) Can't Believe It's Not Better!" at NeurIPS 2021 Workshops}, pages = {64--68}, year = {2022}, editor = {Pradier, Melanie F. and Schein, Aaron and Hyland, Stephanie and Ruiz, Francisco J. R. and Forde, Jessica Z.}, volume = {163}, series = {Proceedings of Machine Learning Research}, month = {13 Dec}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v163/ness22a/ness22a.pdf}, url = {https://proceedings.mlr.press/v163/ness22a.html}, abstract = {Batch Normalizaiton (BN) is a normalization method for deep neural networks that has been shown to accelerate training. While the effectiveness of BN is undisputed, the explanation of its effectiveness is still being studied. The original BN paper attributes the success of BN to reducing internal covariate shift, so we take this a step further and explicitly enforce a Gaussian distribution on hidden layer activations. This approach proves to be ineffective, demonstrating further that reducing internal covariate shift is not important for successful layer normalization.} }
Endnote
%0 Conference Paper %T CDF Normalization for Controlling the Distribution of Hidden Nodes %A Mike Van Ness %A Madeleine Udell %B Proceedings on "I (Still) Can't Believe It's Not Better!" at NeurIPS 2021 Workshops %C Proceedings of Machine Learning Research %D 2022 %E Melanie F. Pradier %E Aaron Schein %E Stephanie Hyland %E Francisco J. R. Ruiz %E Jessica Z. Forde %F pmlr-v163-ness22a %I PMLR %P 64--68 %U https://proceedings.mlr.press/v163/ness22a.html %V 163 %X Batch Normalizaiton (BN) is a normalization method for deep neural networks that has been shown to accelerate training. While the effectiveness of BN is undisputed, the explanation of its effectiveness is still being studied. The original BN paper attributes the success of BN to reducing internal covariate shift, so we take this a step further and explicitly enforce a Gaussian distribution on hidden layer activations. This approach proves to be ineffective, demonstrating further that reducing internal covariate shift is not important for successful layer normalization.
APA
Ness, M.V. & Udell, M.. (2022). CDF Normalization for Controlling the Distribution of Hidden Nodes. Proceedings on "I (Still) Can't Believe It's Not Better!" at NeurIPS 2021 Workshops, in Proceedings of Machine Learning Research 163:64-68 Available from https://proceedings.mlr.press/v163/ness22a.html.

Related Material