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...

Full description

Bibliographic Details

Published in:	Pattern recognition Vol. 136
Main Authors:	Tang, Anda, Niu, Lingfeng, Miao, Jianyu, Zhang, Peng
Format:	Journal Article
Language:	English
Published:	Elsevier Ltd 01.04.2023
Subjects:	[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
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!