arXiv (Cornell University) · 2020 · 148 citations · 28 references
ComputingComputer ScienceComputer VisionFeature EngineeringMachine LearningDeep LearningGradient-based OptimizationNeural NetworksOptimization For Machine LearningPruning StrategiesAccuracyConvolutional Neural NetworksGradient DescentPruningTrainingTraining PruningTraining TimeTraining-time Pruning
Overparameterization has been shown to benefit both the optimization and generalization of neural networks, but large networks are resource hungry at both training and test time. Network pruning can reduce test-time resource requirements, but is typically applied to trained networks and therefore cannot avoid the expensive training process. We aim to prune networks at initialization, thereby saving resources at training time as well. Specifically, we argue that efficient training requires preserving the gradient flow through the network. This leads to a simple but effective pruning criterion we term Gradient Signal Preservation (GraSP). We empirically investigate the effectiveness of the proposed method with extensive experiments on CIFAR-10, CIFAR-100, Tiny-ImageNet and ImageNet, using VGGNet and ResNet architectures. Our method can prune 80% of the weights of a VGG-16 network on ImageNet at initialization, with only a 1.6% drop in top-1 accuracy. Moreover, our method achieves significantly better performance than the baseline at extreme sparsity levels.
28
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2016 · 222.1K citations · Full text
ImageNet: A large-scale hierarchical image database
Jia Deng, Wei Dong, Richard Socher et al. · 2009 IEEE Conference on Computer Vision and Pattern Recognition · 2009 · 61.8K citations
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2015 · 18.8K citations
Automatic differentiation in PyTorch
Adam Paszke, Sam Gross, Soumith Chintala et al. · 2017 · 11.1K citations