loading page

Alternating Block Linearized Bregman Iterations for Regularized Nonnegative Matrix Factorization
  • Beier Chen,
  • Hui Zhang
Beier Chen
National University of Defense Technology
Author Profile
Hui Zhang
National University of Defense Technology

Corresponding Author:h.zhang1984@163.com

Author Profile

Abstract

In this paper, we propose an alternating block variant of the linearized Bregman iterations for a class of regularized nonnegative matrix factorization problems (NMF). The proposed method exploits the block structure of NMF, utilizes the smooth adaptable property of the loss function based on the Bregman distance, and at the same time follows the iterative regularization idea of the linearized Bregman iterations method. Theoretically, we show that the proposed method is a descent method by adjusting the involved parameters. Finally, we end with several illustrative numerical experiments.
02 Jun 2023Submitted to Mathematical Methods in the Applied Sciences
02 Jun 2023Submission Checks Completed
02 Jun 2023Assigned to Editor
09 Jun 2023Review(s) Completed, Editorial Evaluation Pending
09 Jun 2023Reviewer(s) Assigned
05 Feb 20241st Revision Received
07 Feb 2024Assigned to Editor
07 Feb 2024Submission Checks Completed
07 Feb 2024Review(s) Completed, Editorial Evaluation Pending
07 Mar 20242nd Revision Received
09 Mar 2024Submission Checks Completed
09 Mar 2024Assigned to Editor
09 Mar 2024Review(s) Completed, Editorial Evaluation Pending
14 Mar 2024Reviewer(s) Assigned