Decentralized Nonconvex Low-rank Matrix Recovery

For the low-rank matrix recovery problem, algorithms that directly manipulate the low-rank matrix typically require computing the top singular values/vectors of the matrix and thus are computationally expensive. Matrix factorization is a computationally efficient nonconvex approach for low-rank matr...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE transactions on image processing Ročník 34; s. 4806 - 4813
Hlavní autori: Gao, Junzhuo, Lian, Heng
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: United States IEEE 01.01.2025
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:
Algorithms
Approximation algorithms
Approximation error
Convergence
Distributed estimation
Estimation
Factorization
Gradient tracking
Linear convergence
Low-rank estimation
Matrix decomposition
Minimization
Recovery
Signal processing algorithms
Singular value decomposition
Training
Urban areas
ISSN:1057-7149, 1941-0042, 1941-0042
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:For the low-rank matrix recovery problem, algorithms that directly manipulate the low-rank matrix typically require computing the top singular values/vectors of the matrix and thus are computationally expensive. Matrix factorization is a computationally efficient nonconvex approach for low-rank matrix recovery, utilizing an alternating minimization or a gradient descent algorithm, and its theoretical properties have been investigated in recent years. However, the behavior of the factorization-based matrix recovery problem in the decentralized setting is still unknown when data are distributed on multiple nodes. In this paper, we consider the distributed gradient descent algorithm and establish its (local) linear convergence up to the approximation error. Numerical results are also presented to illustrate the convergence of the algorithm over a general network.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1057-7149
1941-0042
1941-0042
DOI:10.1109/TIP.2025.3588719