南方科技大学知识苑(SUSTech KC): A Scale-Invariant Relaxation in Low-Rank Tensor Recovery with an Application to Tensor Completion

题名	A Scale-Invariant Relaxation in Low-Rank Tensor Recovery with an Application to Tensor Completion
作者	Zheng, Huiwen1 ; Lou, Yifei 2,3; Tian, Guoliang1 ; Wang, Chao1,4
通讯作者	Zheng, Huiwen
发表日期	2024
DOI	10.1137/23M1560847
发表期刊	SIAM JOURNAL ON IMAGING SCIENCES 影响因子和分区
ISSN	1936-4954
卷号	17 期号:1
摘要	In this paper, we consider a low -rank tensor recovery problem. Based on the tensor singular value decomposition (t-SVD), we propose the ratio of the tensor nuclear norm and the tensor Frobenius norm (TNF) as a novel nonconvex surrogate of tensor's tubal rank. The rationale of the proposed model for enforcing a low -rank structure is analyzed as its theoretical properties. Specifically, we introduce a null space property (NSP) type condition, under which a low -rank tensor is a local minimum for the proposed TNF recovery model. Numerically, we consider a low -rank tensor completion problem as a specific application of tensor recovery and employ the alternating direction method of multipliers (ADMM) to secure a model solution with guaranteed subsequential convergence under mild conditions. Extensive experiments demonstrate the superiority of our proposed model over state-of-the-art methods.
关键词	tensor singular value decomposition tensor completion tensor tubal rank null space property
相关链接	[来源记录]
收录类别	SCI ; EI
语种	英语
学校署名	第一 ; 通讯
资助项目	NSF grant CAREER[1846690] ; Natural Science Foundation of China[12201286] ; Shenzhen Science and Technology Program[20231115165836001] ; HKRGC[CityU11301120] ; National Key R\&D Program of China[2023YFA1011400] ; Shenzhen Fundamental Research Program[JCYJ20220818100602005]
WOS研究方向	Computer Science ; Mathematics ; Imaging Science & Photographic Technology
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Software Engineering ; Mathematics, Applied ; Imaging Science & Photographic Technology
WOS记录号	WOS:001196417100001
出版者	SIAM PUBLICATIONS
来源库	Web of Science
引用统计
成果类型	期刊论文
条目标识符	http://sustech.caswiz.com/handle/2SGJ60CL/788712
专题	理学院_统计与数据科学系
作者单位	1.Southern Univ Sci & Technol, Dept Stat & Data Sci, Shenzhen 518005, Guangdong, Peoples R China 2.Univ North Carolina Chapel Hill, Dept Math, Chapel Hill, NC 27599 USA 3.Univ North Carolina Chapel Hill, Sch Data Sci & Soc, Chapel Hill, NC 27599 USA 4.Natl Ctr Appl Math Shenzhen, Shenzhen 518055, Guangdong, Peoples R China
第一作者单位	统计与数据科学系
通讯作者单位	统计与数据科学系
第一作者的第一单位	统计与数据科学系
推荐引用方式 GB/T 7714	Zheng, Huiwen,Lou, Yifei,Tian, Guoliang,et al. A Scale-Invariant Relaxation in Low-Rank Tensor Recovery with an Application to Tensor Completion[J]. SIAM JOURNAL ON IMAGING SCIENCES,2024,17(1).
APA	Zheng, Huiwen,Lou, Yifei,Tian, Guoliang,&Wang, Chao.(2024).A Scale-Invariant Relaxation in Low-Rank Tensor Recovery with an Application to Tensor Completion.SIAM JOURNAL ON IMAGING SCIENCES,17(1).
MLA	Zheng, Huiwen,et al."A Scale-Invariant Relaxation in Low-Rank Tensor Recovery with an Application to Tensor Completion".SIAM JOURNAL ON IMAGING SCIENCES 17.1(2024).