An Improved Alternating Direction Method of Multipliers for Matrix Completion

Matrix completion is widely used in information science fields such as machine learning and image processing. The alternating direction method of multipliers (ADMM), due to its ability to utilize the separable structure of the objective function, has become an extremely popular approach for solving...

Full description

Saved in:
Bibliographic Details
Published in:Foundations of computing and decision sciences 2024-02, Vol.49 (1), p.49-62
Main Authors: Yan, Xihong, Zhang, Ning, Li, Hao
Format: Article
Language:English
Subjects:
alternating direction method of multipliers
matrix completion
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Matrix completion is widely used in information science fields such as machine learning and image processing. The alternating direction method of multipliers (ADMM), due to its ability to utilize the separable structure of the objective function, has become an extremely popular approach for solving this problem. But its subproblems can be computationally demanding. In order to improve computational e ciency, for large scale matrix completion problems, this paper proposes an improved ADMM by using convex combination technique. Under certain assumptions, the global convergence of the new algorithm is proved. Finally, we demonstrate the performance of the proposed algorithms via numerical experiments.
ISSN:2300-3405
2300-3405
DOI:10.2478/fcds-2024-0004