Scaling Up Exact Neural Network Compression by ReLU Stability

Thiago Serra, Xin Yu, Abhinav Kumar, Srikumar Ramalingam

Keywords: Scaling, Neural Networks, Lossless Compression, ReLU

Abstract: We can compress a rectifier network while exactly preserving its underlying functionality with respect to a given input domain if some of its neurons are stable. However, current approaches to determine the stability of neurons with Rectified Linear Unit (ReLU) activations require solving or finding a good approximation to multiple discrete optimization problems. In this work, we introduce an algorithm based on solving a single optimization problem to identify all stable neurons. Our approach is on median 183 times faster than the state-of-art method on CIFAR-10, which allows us to explore exact compression on deeper (5 x 100) and wider (2 x 800) networks within minutes. For classifiers trained under an amount of L1 regularization that does not worsen accuracy, we can remove up to 56% of the connections on the CIFAR-10 dataset. The code is available at the following link, https://github.com/yuxwind/ExactCompression .

Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.

Code: https://github.com/yuxwind/ExactCompression

TL;DR: We scale up the lossless compression in ReLU neural network based on solving a single optimization problem to identify all stable neurons.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2102.07804/code)