A concave-regularized relaxed binary mask, pruned by threshold and rewound, finds sparse trainable subnetworks with accuracy comparable to or better than iterative magnitude pruning.
Learning sparse neural networks through ℓ0 regularization,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Playing the Lottery With Concave Regularizers for Sparse Trainable Neural Networks
A concave-regularized relaxed binary mask, pruned by threshold and rewound, finds sparse trainable subnetworks with accuracy comparable to or better than iterative magnitude pruning.