Model pruning is a popular mechanism to make a network more efficient for inference. In this paper, we explore the use of pruning to also make the training of such neural networks more efficient. Unlike all prior model pruning methods that sparsify a pre-trained model and then prune it, we train the network from scratch, while gradually and structurally pruning parameters during the training. We build on our key observations: 1) once parameters are sparsified via regularization, they rarely re-appear in later steps, and 2) setting the appropriate regularization penalty at the beginning of training effectively converges the loss. We train ResNet and VGG networks on CIFAR10/100 and ImageNet datasets from scratch, and achieve 30-50% improvement in training FLOPs and 20-30% improvement in measured training time on modern GPUs.

我们提出了PruneTrain，这是一种成本高效的机制，可逐步减少训练期间的计算成本，通过使用结构化组套骨骼正则化方法和其他重新配置技术，可以在GPU加速器上高效处理缩小了的卷积神经网络模型，从而实现减少计算成本40％和训练时间39％的效果。

PruneTrain: 动态稀疏模型重组快速神经网络训练