Exploiting Non-Linear Redundancy for Neural Model Compression

TL;DR

This paper introduces a novel, provably lossless neural network compression method that exploits linear dependencies among neurons, achieving up to 99% size reduction with minimal performance loss.

Contribution

The paper presents a new compression technique based on eliminating neurons via linear dependence, combined with an annealing algorithm, applicable during or after training.

Findings

Up to 99% reduction in network size achieved.

Method is lossless during training and effective on trained models.

Theoretical proof of capturing redundancies in overparametrized ReLU networks.

Abstract

Deploying deep learning models, comprising of non-linear combination of millions, even billions, of parameters is challenging given the memory, power and compute constraints of the real world. This situation has led to research into model compression techniques most of which rely on suboptimal heuristics and do not consider the parameter redundancies due to linear dependence between neuron activations in overparametrized networks. In this paper, we propose a novel model compression approach based on exploitation of linear dependence, that compresses networks by elimination of entire neurons and redistribution of their activations over other neurons in a manner that is provably lossless while training. We combine this approach with an annealing algorithm that may be applied during training, or even on a trained model, and demonstrate, using popular datasets, that our method results in a reduction of up to 99\% in overall network size with small loss in performance. Furthermore, we provide theoretical results showing that in overparametrized, locally linear (ReLU) neural networks where redundant features exist, and with correct hyperparameter selection, our method is indeed able to capture and suppress those dependencies.