Sparse Networks from Scratch: Faster Training without Losing Performance

Open paper
Benchmark Model Rank Results
image-classification-on-cifar-10WRN-22-8 (Sparse Momentum)#138Percentage correct: 95.04
image-classification-on-mnistLeNet 300-100 (Sparse Momentum)#37Percentage error: 1.26

Rank counts only results with a code link.