Picking Winning Tickets Before Training by Preserving Gradient Flow

Chaoqi Wang, Guodong Zhang, Roger Grosse

Keywords: generalization, imagenet, optimization, pruning

Abstract: 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. Our code is made public at: https://github.com/alecwangcq/GraSP.

Similar Papers

Adversarial AutoAugment
Xinyu Zhang, Qiang Wang, Jian Zhang, Zhao Zhong,
Batch-shaping for learning conditional channel gated networks
Babak Ehteshami Bejnordi, Tijmen Blankevoort, Max Welling,
Lookahead: A Far-sighted Alternative of Magnitude-based Pruning
Sejun Park, Jaeho Lee, Sangwoo Mo, Jinwoo Shin,