Sparse Networks from Scratch: Faster Training without Losing Performance

ICLR 2020  ·  Tim Dettmers, Luke Zettlemoyer ·

We demonstrate the possibility of what we call sparse learning: accelerated training of deep neural networks that maintain sparse weights throughout training while achieving dense performance levels. We accomplish this by developing sparse momentum, an algorithm which uses exponentially smoothed gradients (momentum) to identify layers and weights which reduce the error efficiently. Sparse momentum redistributes pruned weights across layers according to the mean momentum magnitude of each layer. Within a layer, sparse momentum grows weights according to the momentum magnitude of zero-valued weights. We demonstrate state-of-the-art sparse performance on MNIST, CIFAR-10, and ImageNet, decreasing the mean error by a relative 8%, 15%, and 6% compared to other sparse algorithms. Furthermore, we show that sparse momentum reliably reproduces dense performance levels while providing up to 5.61x faster training. In our analysis, ablations show that the benefits of momentum redistribution and growth increase with the depth and size of the network. Additionally, we find that sparse momentum is insensitive to the choice of its hyperparameters suggesting that sparse momentum is robust and easy to use.

PDF Abstract ICLR 2020 PDF ICLR 2020 Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Image Classification CIFAR-10 WRN-22-8 (Sparse Momentum) Percentage correct 95.04 # 128
Image Classification MNIST LeNet 300-100 (Sparse Momentum) Percentage error 1.26 # 68

Methods


No methods listed for this paper. Add relevant methods here