Nonconvex Demixing From Bilinear Measurements

doi:10.1109/TSP.2018.2864660

	Nonconvex Demixing From Bilinear Measurements
	Dong, Jialin; Shi, Yuanming
	2018-10-01
发表期刊	IEEE TRANSACTIONS ON SIGNAL PROCESSING (IF:4.6[JCR-2023],5.2[5-Year])
ISSN	1053-587X
EISSN	1941-0476
卷号	66 期号:19 页码:5152-5166
发表状态	已发表
DOI	10.1109/TSP.2018.2864660
摘要	We consider the problem of demixing a sequence of source signals from the sum of noisy bilinear measurements. It is a generalized mathematical model for blind demixing with blind deconvolution, which is prevalent across the areas of dictionary learning, image processing, and communications. However, state-of-the-art convex methods for blind demixing via semidefinite programming are computationally infeasible for large-scale problems. Although the existing nonconvex algorithms are able to address the scaling issue, they normally require proper regularization to establish optimality guarantees. The additional regularization yields tedious algorithmic parameters and pessimistic convergence rates with conservative step sizes. To address the limitations of exiting methods, we thus develop a provable nonconvex demixing procedure via Wirtinger flow, much like vanilla gradient descent, to harness the benefits of regularization-free fast convergence rate with aggressive step size and computational optimality guarantees. This is achieved by exploiting the benign geometry of the blind demixing problem, thereby revealing that Wirtinger flow enforces the regularization-free iterates in the region of strong convexity and qualified level of smoothness, where the step size can be chosen aggressively.
关键词	Blind demixing blind deconvolution bilinear measurements nonconvex optimization Wirtinger flow regularization-free statistical and computational guarantee Blind Demixing Blind Deconvolution Bilinear Measurements Nonconvex Optimization Wirtinger Flow
URL	查看原文
收录类别	SCIE ; EI ; SCI
语种	英语
WOS研究方向	Engineering
WOS类目	Engineering, Electrical & Electronic
WOS记录号	WOS:000443987600007
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
原始文献类型	Article
引用统计	正在获取...
文献类型	期刊论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/243316
专题	信息科学与技术学院_硕士生信息科学与技术学院_PI研究组_石远明组
通讯作者	Shi, Yuanming
作者单位	ShanghaiTech Univ, Sch Informat Sci & Technol, Shanghai 201210, Peoples R China
第一作者单位	信息科学与技术学院
通讯作者单位	信息科学与技术学院
第一作者的第一单位	信息科学与技术学院
推荐引用方式 GB/T 7714	Dong, Jialin,Shi, Yuanming. Nonconvex Demixing From Bilinear Measurements[J]. IEEE TRANSACTIONS ON SIGNAL PROCESSING,2018,66(19):5152-5166.
APA	Dong, Jialin,&Shi, Yuanming.(2018).Nonconvex Demixing From Bilinear Measurements.IEEE TRANSACTIONS ON SIGNAL PROCESSING,66(19),5152-5166.
MLA	Dong, Jialin,et al."Nonconvex Demixing From Bilinear Measurements".IEEE TRANSACTIONS ON SIGNAL PROCESSING 66.19(2018):5152-5166.