Abstract | ||
---|---|---|
Sparsity in Deep Neural Networks (DNNs) is studied extensively with the focus of maximizing prediction accuracy given an overall budget. Existing methods rely on uniform or heuristic non-uniform sparsity budgets which have sub-optimal layer-wise parameter allocation resulting in a) lower prediction accuracy or b) higher inference cost (FLOPs). This work proposes Soft Threshold Reparameterization (STR), a novel use of the soft-threshold operator on DNN weights. STR smoothly induces sparsity while learning pruning thresholds thereby obtaining a non-uniform sparsity budget. Our method achieves state-of-the-art accuracy for unstructured sparsity in CNNs (ResNet50 and MobileNetV1 on ImageNet-1K), and, additionally, learns non-uniform budgets that empirically reduce the FLOPs by up to 50%. Notably, STR boosts the accuracy over existing results by up to 10% in the ultra sparse (99%) regime and can also be used to induce low-rank (structured sparsity) in RNNs. In short, STR is a simple mechanism which learns effective sparsity budgets that contrast with popular heuristics. |
Year | Venue | DocType |
---|---|---|
2020 | ICML | Conference |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Aditya Kusupati | 1 | 4 | 2.77 |
Ramanujan Vivek | 2 | 0 | 1.01 |
Raghav Somani | 3 | 0 | 2.03 |
Mitchell Wortsman | 4 | 3 | 2.74 |
Jain Prateek | 5 | 0 | 0.34 |
Sham Kakade | 6 | 4365 | 282.77 |
Ali Farhadi | 7 | 4492 | 190.40 |