A dynamic sparse training method that restricts weights to a learnable set of diagonals, preserving sparsity in both forward and backward passes to obtain GPU speedups at accuracy close to unstructured sparsity.
Which layer is learning faster? a systematic exploration of layer-wise convergence rate for deep neural networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Dynamic Sparse Training of Diagonally Sparse Networks
A dynamic sparse training method that restricts weights to a learnable set of diagonals, preserving sparsity in both forward and backward passes to obtain GPU speedups at accuracy close to unstructured sparsity.