Learning Sparsity and Quantization Jointly and Automatically for Neural Network Compression via Constrained Optimization

by   Haichuan Yang, et al.

Deep Neural Networks (DNNs) are widely applied in a wide range of usecases. There is an increased demand for deploying DNNs on devices that do not have abundant resources such as memory and computation units. Recently, network compression through a variety of techniques such as pruning and quantization have been proposed to reduce the resource requirement. A key parameter that all existing compression techniques are sensitive to is the compression ratio (e.g., pruning sparsity, quantization bitwidth) of each layer. Traditional solutions treat the compression ratios of each layer as hyper-parameters, and tune them using human heuristic. Recent researchers start using black-box hyper-parameter optimizations, but they will introduce new hyper-parameters and have efficiency issue. In this paper, we propose a framework to jointly prune and quantize the DNNs automatically according to a target model size without using any hyper-parameters to manually set the compression ratio for each layer. In the experiments, we show that our framework can compress the weights data of ResNet-50 to be 836x smaller without accuracy loss on CIFAR-10, and compress AlexNet to be 205x smaller without accuracy loss on ImageNet classification.


page 1

page 2

page 3

page 4


OPQ: Compressing Deep Neural Networks with One-shot Pruning-Quantization

As Deep Neural Networks (DNNs) usually are overparameterized and have mi...

Toward Compact Parameter Representations for Architecture-Agnostic Neural Network Compression

This paper investigates deep neural network (DNN) compression from the p...

A Programmable Approach to Model Compression

Deep neural networks frequently contain far more weights, represented at...

DeepSZ: A Novel Framework to Compress Deep Neural Networks by Using Error-Bounded Lossy Compression

DNNs have been quickly and broadly exploited to improve the data analysi...

GNN-RL Compression: Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learning

Model compression is an essential technique for deploying deep neural ne...

Network Automatic Pruning: Start NAP and Take a Nap

Network pruning can significantly reduce the computation and memory foot...

AdaComp : Adaptive Residual Gradient Compression for Data-Parallel Distributed Training

Highly distributed training of Deep Neural Networks (DNNs) on future com...

Please sign up or login with your details

Forgot password? Click here to reset