Stochastic privacy-preserving methods for nonconvex sparse learning

Sparse learning is essential in mining high-dimensional data. Iterative hard thresholding (IHT) methods are effective for optimizing nonconvex objectives for sparse learning. However, IHT methods are vulnerable to adversary attacks that infer sensitive data. Although pioneering works attempted to re...

Full description

Bibliographic Details

Published in:	Information sciences Vol. 630; pp. 567 - 585
Main Authors:	Liang, Guannan, Tong, Qianqian, Ding, Jiahao, Pan, Miao, Bi, Jinbo
Format:	Journal Article
Language:	English
Published:	Elsevier Inc 01.06.2023
Subjects:	Differential privacy Sparse learning Stochastic algorithm Differential privacy Stochastic algorithm Sparse learning
ISSN:	0020-0255, 1872-6291
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!