# Scalable Model Compression by Entropy Penalized Reparameterization

Source: [Scalable Model Compression by Entropy Penalized Reparameterization](<https://www.sota2.com/research/paper/68fa67041e209131cea13c86>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T22:04:19.938Z

Authors: Deniz Oktay, Johannes Ball\\'e, Saurabh Singh, Abhinav Shrivastava

Published: 2019-06-15T22:46:33.000Z

## Abstract

We describe a simple and general neural network weight compression approach, in which the network parameters (weights and biases) are represented in a "latent" space, amounting to a reparameterization. This space is equipped with a learned probability model, which is used to impose an entropy penalty on the parameter representation during training, and to compress the representation using a simple arithmetic coder after training. Classification accuracy and model compressibility is maximized jointly, with the bitrate--accuracy trade-off specified by a hyperparameter. We evaluate the method on the MNIST, CIFAR-10 and ImageNet classification benchmarks using six distinct model architectures. Our results show that state-of-the-art model compression can be achieved in a scalable and general way without requiring complex procedures such as multi-stage training.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1906.06624>)

[PDF](<https://arxiv.org/pdf/1906.06624.pdf>)