Training Compact DNNs with ℓ1/2 Regularization

•We propose a network compression model based on ℓ1/2 regularization. To the best of our knowledge, it is the first work utilizing non-Lipschitz continuous regularization to compress DNNs.•We strictly prove the correspondence between ℓp(0<p<1) and Hyper-Laplacian prior. Based on this prior, we...

Celý popis

Podrobná bibliografia

Vydané v:	Pattern recognition Ročník 136
Hlavní autori:	Tang, Anda, Niu, Lingfeng, Miao, Jianyu, Zhang, Peng
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Elsevier Ltd 01.04.2023
Predmet:	[formula omitted] Quasi-norm Deep neural networks Model compression Non-Lipschitz regularization Sparse optimization Sparse optimization Deep neural networks Model compression Non-Lipschitz regularization ℓ1/2 Quasi-norm
ISSN:	0031-3203, 1873-5142
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!