Nonconvex Demixing from Bilinear Measurements
Dong, Jialin; Shi, Yuanming
2018
Source Publication2018 IEEE INTERNATIONAL SYMPOSIUM ON INFORMATION THEORY (ISIT)
Volume66
Issue19
Pages666-670
Status已发表
DOI10.1109/TSP.2018.2864660
AbstractWe consider the problem of demixing a sequence of source signals from the sum of bilinear measurements. It is a generalized mathematical model of blind demixing with deconvolution, which has wide applications in communication, image processing and dictionary learning, etc. However, state-of-art algorithms for blind demixing either fail to scale to large problem sizes or require proper regularization with tedious algorithmic parameters for optimality guarantees. To address the limitations of exiting methods, we propose a provable nonconvex demixing procedure via Wirtinger flow, much like vanilla gradient descent, to harness the benefits of regularization free, fast convergence rate, and optimality guarantees. This is achieved by exploiting the benign geometry of blind demixing, thereby revealing that Wirtinger flow enforces the iterates in the region of strong convexity and qualified level of smoothness.
KeywordBlind demixing blind deconvolution bilinear measurements nonconvex optimization Wirtinger flow regularization-free statistical and computational guarantee
Conference PlaceVail, CO
Conference Date17-22 June 2018
URL查看原文
Indexed ByEI ; SCI ; CPCI
Language英语
Funding ProjectShanghai Sailing Program[16YF1407700]
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Information Systems ; Engineering, Electrical & Electronic
WOS IDWOS:000448139300134
PublisherIEEE
EI Accession Number20183605765148
EI KeywordsImage processing ; Optimization
EI Classification NumberInformation Theory and Signal Processing:716.1 ; Optimization Techniques:921.5
WOS KeywordBLIND DECONVOLUTION
Original Document TypeProceedings Paper
Citation statistics
Cited Times:17[WOS]   [WOS Record]     [Related Records in WOS]
Document Type会议论文
Identifierhttps://kms.shanghaitech.edu.cn/handle/2MSLDSTB/27685
Collection信息科学与技术学院
信息科学与技术学院_PI研究组_石远明组
信息科学与技术学院_硕士生
Corresponding AuthorDong, Jialin
AffiliationShanghaiTech Univ, Sch Informat Sci & Technol, Shanghai 201210, Peoples R China
First Author AffilicationSchool of Information Science and Technology
Corresponding Author AffilicationSchool of Information Science and Technology
First Signature AffilicationSchool of Information Science and Technology
Recommended Citation
GB/T 7714
Dong, Jialin,Shi, Yuanming. Nonconvex Demixing from Bilinear Measurements[C]:IEEE,2018:666-670.
Files in This Item: Download All
File Name/Size DocType Version Access License
10.1109@ISIT.2018.84(520KB)会议论文作者原稿开放获取UnknownView Download
Related Services
Usage statistics
Scholar Google
Similar articles in Scholar Google
[Dong, Jialin]'s Articles
[Shi, Yuanming]'s Articles
Baidu academic
Similar articles in Baidu academic
[Dong, Jialin]'s Articles
[Shi, Yuanming]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Dong, Jialin]'s Articles
[Shi, Yuanming]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 10.1109@ISIT.2018.8437562.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.