An Information-Theoretic Justification for Model Pruning

We study the neural network (NN) compression problem, viewing the tension between the compression ratio and NN performance through the lens of rate-distortion theory. We choose a distortion metric that reflects the effect of NN compression on the model output and derive the tradeoff between rate (co...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Isik, Berivan, Weissman, Tsachy, Albert No
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 09.02.2022
Subjects
Compression ratio
Data compression
Distortion
Information theory
Neural networks
Pruning
Online AccessGet full text

Cover

More Information
Summary:We study the neural network (NN) compression problem, viewing the tension between the compression ratio and NN performance through the lens of rate-distortion theory. We choose a distortion metric that reflects the effect of NN compression on the model output and derive the tradeoff between rate (compression) and distortion. In addition to characterizing theoretical limits of NN compression, this formulation shows that \emph{pruning}, implicitly or explicitly, must be a part of a good compression algorithm. This observation bridges a gap between parts of the literature pertaining to NN and data compression, respectively, providing insight into the empirical success of model pruning. Finally, we propose a novel pruning strategy derived from our information-theoretic formulation and show that it outperforms the relevant baselines on CIFAR-10 and ImageNet datasets.
ISSN:2331-8422