Automatic Neural Network Compression by Sparsity-Quantization Joint Learning: A Constrained Optimization-based Approach
arXiv:1910.05897
Abstract
Deep Neural Networks (DNNs) are 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 836 smaller without accuracy loss on CIFAR-10, and compress AlexNet to be 205 smaller without accuracy loss on ImageNet classification.
References in corpus (26)
- Continuous control with deep reinforcement learning
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1
- SGDR: Stochastic Gradient Descent with Warm Restarts
- Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations
- Pruning Convolutional Neural Networks for Resource Efficient Inference
- AMC: AutoML for Model Compression and Acceleration on Mobile Devices
- Compressing Deep Convolutional Networks using Vector Quantization
- Ternary Weight Networks
- Trained Ternary Quantization
- Pruning Filters for Efficient ConvNets
- A Systematic DNN Weight Pruning Framework using Alternating Direction Method of Multipliers
- Convolutional Neural Networks using Logarithmic Data Representation
- Bayesian Compression for Deep Learning
- Single Path One-Shot Neural Architecture Search with Uniform Sampling
- Reproducibility of Benchmarked Deep Reinforcement Learning Tasks for Continuous Control
- Rethinking the Smaller-Norm-Less-Informative Assumption in Channel Pruning of Convolution Layers
- MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning
- Deep -Means: Re-Training and Parameter Sharing with Harder Cluster Assignments for Compressing Deep Convolutions
- Extremely Low Bit Neural Network: Squeeze the Last Bit Out with ADMM
- Towards the Limit of Network Quantization
- Model Compression with Adversarial Robustness: A Unified Optimization Framework
- ReLeQ: A Reinforcement Learning Approach for Deep Quantization of Neural Networks
- A Unified Framework of DNN Weight Pruning and Weight Clustering/Quantization Using ADMM
- Energy-Constrained Compression for Deep Neural Networks via Weighted Sparse Projection and Layer Input Masking
- Progressive DNN Compression: A Key to Achieve Ultra-High Weight Pruning and Quantization Rates using ADMM