Generalized nonconvex nonsmooth low-rank matrix recovery framework with feasible algorithm designs and convergence analysis
Download
Download
Download
Full text for this resource is not available from the Research Repository.
Export
Zhang, Hengmin 
ORCID: 0000-0002-2472-6637, Qian, Feng ORCID: 0000-0003-2781-332X, Shi, Peng ORCID: 0000-0001-8218-586X, Du, Wenli ORCID: 0000-0002-2676-6341, Tang, Yang ORCID: 0000-0002-2750-8029, Qian, Jianjun ORCID: 0000-0002-0968-8556, Gong, Chen ORCID: 0000-0002-4092-9856 and Yang, Jian ORCID: 0000-0003-4800-832X
(2022)
Generalized nonconvex nonsmooth low-rank matrix recovery framework with feasible algorithm designs and convergence analysis.
IEEE Transactions on Neural Networks and Learning Systems.
pp. 1-12.
ISSN 2162-237X
Dimensions Badge
Altmetric Badge
| Item type | Article |
| URI | https://vuir.vu.edu.au/id/eprint/46506 |
| DOI | 10.1109/TNNLS.2022.3183970 |
| Official URL | https://ieeexplore.ieee.org/document/9805680/ |
| Subjects | Current > FOR (2020) Classification > 4602 Artificial intelligence Current > Division/Research > College of Science and Engineering |
| Keywords | algorithm, data matrix, matrix recovery problem, alternating direction method of multiplier, ADMM, minimisation framework |
| Download/View statistics | View download statistics for this item |
CORE (COnnecting REpositories)