Accelerating Gradient Descent for Over-Parameterized Asymmetric Low-Rank Matrix Sensing via Preconditioning

doi:10.1109/ICASSP48485.2024.10446187

	Accelerating Gradient Descent for Over-Parameterized Asymmetric Low-Rank Matrix Sensing via Preconditioning
	Cheng Cheng; Ziping Zhao
	2024-04
会议录名称	ICASSP 2024 - 2024 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)
ISSN	1520-6149
页码	7705-7709
发表状态	已发表
DOI	10.1109/ICASSP48485.2024.10446187
摘要	We present an accelerated method for the asymmetric low-rank matrix sensing problem in the over-parameterized setup, named preconditioned gradient descent. We analyze the local convergence rate of the proposed algorithm starting from spectral initialization. Our algorithm is shown to have linear convergence rate independent of condition number even when ill-conditioning and over-parameterization both exist in the asymmetric matrix sensing problem. Numerical results verify the theoretical findings and demonstrate the performance of the proposed algorithm. © 2024 IEEE.
会议录编者/会议主办者	The Institute of Electrical and Electronics Engineers Signal Processing Society
关键词	Low-rank matrix sensing matrix recovery preconditioned gradient descent over-parameterization
会议名称	49th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024
会议地点	Seoul, Korea, Republic of
会议日期	14-19 April 2024
URL	查看原文
收录类别	EI
语种	英语
出版者	Institute of Electrical and Electronics Engineers Inc.
EI入藏号	20242416240239
原始文献类型	Conference article (CA)
来源库	IEEE
文献类型	会议论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/354936
专题	信息科学与技术学院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_赵子平组
作者单位	School of Information Science and Technology, ShanghaiTech University, Shanghai, China
第一作者单位	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	Cheng Cheng,Ziping Zhao. Accelerating Gradient Descent for Over-Parameterized Asymmetric Low-Rank Matrix Sensing via Preconditioning[C]//The Institute of Electrical and Electronics Engineers Signal Processing Society:Institute of Electrical and Electronics Engineers Inc.,2024:7705-7709.