Pith. sign in

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 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

Dynamic Sparse Training of Diagonally Sparse Networks

cs.LG · 2025-06-13 · conditional · novelty 6.0

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.

citing papers explorer

Showing 1 of 1 citing paper.

  • Dynamic Sparse Training of Diagonally Sparse Networks cs.LG · 2025-06-13 · conditional · none · ref 5

    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.