Quasi-Newton method for sparse matrix factorization with frobenius norm regularization

This paper considers quasi-Newton method for sparse matrix factorization (SMF) that incorporates Frobenius norm regularization to control overfitting and enhance generalization in data-driven applications. Sparse matrix factorization seeks to decompose a matrix into 2 matrices while promoting sparsi...

Full description

Bibliographic Details
Main Authors: June, Leong Wah, Ab Rahmin, Nor Aliza, Peng, Lim Fong, Firdaus Faris, Muhammad Yusril
Format: Article
Language:English
Published: Persatuan Sains Matematik Malaysia 2024
Online Access:http://psasir.upm.edu.my/id/eprint/120306/
http://psasir.upm.edu.my/id/eprint/120306/1/120306.pdf
_version_ 1848868159061229568
author June, Leong Wah
Ab Rahmin, Nor Aliza
Peng, Lim Fong
Firdaus Faris, Muhammad Yusril
author_facet June, Leong Wah
Ab Rahmin, Nor Aliza
Peng, Lim Fong
Firdaus Faris, Muhammad Yusril
author_sort June, Leong Wah
building UPM Institutional Repository
collection Online Access
description This paper considers quasi-Newton method for sparse matrix factorization (SMF) that incorporates Frobenius norm regularization to control overfitting and enhance generalization in data-driven applications. Sparse matrix factorization seeks to decompose a matrix into 2 matrices while promoting sparsity in one (or both) of the resulting factors, which is particularly useful in applications such as recommendation systems, signal processing, and dimensionality reduction. The Frobenius norm regularization is employed to penalize large parameter values, ensuring sparser factorization. The proposed quasi-Newton method, leveraging approximate second-order information, efficiently optimizes the objective function with significantly reduced computational overhead compared to full Newton methods. Experimental results on an example demonstrate the efficacy of the method in achieving high-quality sparse factorizations under different regularization parameter.
first_indexed 2025-11-15T14:47:57Z
format Article
id upm-120306
institution Universiti Putra Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T14:47:57Z
publishDate 2024
publisher Persatuan Sains Matematik Malaysia
recordtype eprints
repository_type Digital Repository
spelling upm-1203062025-09-30T03:50:51Z http://psasir.upm.edu.my/id/eprint/120306/ Quasi-Newton method for sparse matrix factorization with frobenius norm regularization June, Leong Wah Ab Rahmin, Nor Aliza Peng, Lim Fong Firdaus Faris, Muhammad Yusril This paper considers quasi-Newton method for sparse matrix factorization (SMF) that incorporates Frobenius norm regularization to control overfitting and enhance generalization in data-driven applications. Sparse matrix factorization seeks to decompose a matrix into 2 matrices while promoting sparsity in one (or both) of the resulting factors, which is particularly useful in applications such as recommendation systems, signal processing, and dimensionality reduction. The Frobenius norm regularization is employed to penalize large parameter values, ensuring sparser factorization. The proposed quasi-Newton method, leveraging approximate second-order information, efficiently optimizes the objective function with significantly reduced computational overhead compared to full Newton methods. Experimental results on an example demonstrate the efficacy of the method in achieving high-quality sparse factorizations under different regularization parameter. Persatuan Sains Matematik Malaysia 2024 Article PeerReviewed text en http://psasir.upm.edu.my/id/eprint/120306/1/120306.pdf June, Leong Wah and Ab Rahmin, Nor Aliza and Peng, Lim Fong and Firdaus Faris, Muhammad Yusril (2024) Quasi-Newton method for sparse matrix factorization with frobenius norm regularization. Menemui Matematik, 46 (3). pp. 20-26. ISSN 2231-7023 https://persama.org.my/images/Menemui_Matematik/2024/MMv463_13_19.pdf
spellingShingle June, Leong Wah
Ab Rahmin, Nor Aliza
Peng, Lim Fong
Firdaus Faris, Muhammad Yusril
Quasi-Newton method for sparse matrix factorization with frobenius norm regularization
title Quasi-Newton method for sparse matrix factorization with frobenius norm regularization
title_full Quasi-Newton method for sparse matrix factorization with frobenius norm regularization
title_fullStr Quasi-Newton method for sparse matrix factorization with frobenius norm regularization
title_full_unstemmed Quasi-Newton method for sparse matrix factorization with frobenius norm regularization
title_short Quasi-Newton method for sparse matrix factorization with frobenius norm regularization
title_sort quasi-newton method for sparse matrix factorization with frobenius norm regularization
url http://psasir.upm.edu.my/id/eprint/120306/
http://psasir.upm.edu.my/id/eprint/120306/
http://psasir.upm.edu.my/id/eprint/120306/1/120306.pdf