A fast correction approach to tensor robust principal component analysis
Tensor robust principal component analysis (TRPCA) is a useful approach for obtaining low-rank data corrupted by noise or outliers. However, existing TRPCA methods face certain challenges when it comes to estimating the tensor rank and the sparsity accurately. The commonly used tensor nuclear norm (...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/180347 |
| _version_ | 1824453529551503360 |
|---|---|
| author | Zhang, Zhechen Liu, Sanyang Lin, Zhiping Xue, Jize Liu, Lixia |
| author2 | School of Electrical and Electronic Engineering |
| author_facet | School of Electrical and Electronic Engineering Zhang, Zhechen Liu, Sanyang Lin, Zhiping Xue, Jize Liu, Lixia |
| author_sort | Zhang, Zhechen |
| collection | NTU |
| description | Tensor robust principal component analysis (TRPCA) is a useful approach for obtaining low-rank data corrupted by noise or outliers. However, existing TRPCA methods face certain challenges when it comes to estimating the tensor rank and the sparsity accurately. The commonly used tensor nuclear norm (TNN) may lead to sub-optimal solutions due to the gap between TNN and the tensor rank. Additionally, the ℓ1-norm is not an ideal estimation of the ℓ0-norm, and solving TNN minimization can be computationally intensive because of the tensor singular value thresholding (t-SVT) scheme. To address these issues, a method called fast correction TNN (FC-TNN) is proposed for TRPCA. In contrast to existing methods, FC-TNN introduces a correction term to bridge the gap between TNN and the tensor rank. Furthermore, a new correction term is employed for the ℓ1-norm to achieve the desired solution. To improve computational efficiency, the Chebyshev polynomial approximation (CPA) technique is presented for computing t-SVT without requiring tensor singular value decomposition (t-SVD). The CPA technique is incorporated into the alternating direction method of multipliers (ADMM) algorithm to solve the proposed model effectively. Theoretical analysis demonstrates that FC-TNN offers a lower error bound compared to TNN under certain conditions. Extensive experiments conducted on various tensor-based datasets illustrate that the proposed method outperforms several state-of-the-art methods. |
| first_indexed | 2025-02-19T03:07:52Z |
| format | Journal Article |
| id | ntu-10356/180347 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2025-02-19T03:07:52Z |
| publishDate | 2024 |
| record_format | dspace |
| spelling | ntu-10356/1803472024-10-02T05:59:39Z A fast correction approach to tensor robust principal component analysis Zhang, Zhechen Liu, Sanyang Lin, Zhiping Xue, Jize Liu, Lixia School of Electrical and Electronic Engineering Engineering Tensor nuclear norm Tensor singular value decomposition Tensor robust principal component analysis (TRPCA) is a useful approach for obtaining low-rank data corrupted by noise or outliers. However, existing TRPCA methods face certain challenges when it comes to estimating the tensor rank and the sparsity accurately. The commonly used tensor nuclear norm (TNN) may lead to sub-optimal solutions due to the gap between TNN and the tensor rank. Additionally, the ℓ1-norm is not an ideal estimation of the ℓ0-norm, and solving TNN minimization can be computationally intensive because of the tensor singular value thresholding (t-SVT) scheme. To address these issues, a method called fast correction TNN (FC-TNN) is proposed for TRPCA. In contrast to existing methods, FC-TNN introduces a correction term to bridge the gap between TNN and the tensor rank. Furthermore, a new correction term is employed for the ℓ1-norm to achieve the desired solution. To improve computational efficiency, the Chebyshev polynomial approximation (CPA) technique is presented for computing t-SVT without requiring tensor singular value decomposition (t-SVD). The CPA technique is incorporated into the alternating direction method of multipliers (ADMM) algorithm to solve the proposed model effectively. Theoretical analysis demonstrates that FC-TNN offers a lower error bound compared to TNN under certain conditions. Extensive experiments conducted on various tensor-based datasets illustrate that the proposed method outperforms several state-of-the-art methods. This research has been supported by the National Natural Science Foundation of China (No.12271419) and the Natural Science Basic Research Program of Shaanxi (Program No.2023-JC-YB-056). 2024-10-02T05:59:39Z 2024-10-02T05:59:39Z 2024 Journal Article Zhang, Z., Liu, S., Lin, Z., Xue, J. & Liu, L. (2024). A fast correction approach to tensor robust principal component analysis. Applied Mathematical Modelling, 128, 195-219. https://dx.doi.org/10.1016/j.apm.2024.01.020 0307-904X https://hdl.handle.net/10356/180347 10.1016/j.apm.2024.01.020 2-s2.0-85184993043 128 195 219 en Applied Mathematical Modelling © 2024 Elsevier Inc. All rights reserved. |
| spellingShingle | Engineering Tensor nuclear norm Tensor singular value decomposition Zhang, Zhechen Liu, Sanyang Lin, Zhiping Xue, Jize Liu, Lixia A fast correction approach to tensor robust principal component analysis |
| title | A fast correction approach to tensor robust principal component analysis |
| title_full | A fast correction approach to tensor robust principal component analysis |
| title_fullStr | A fast correction approach to tensor robust principal component analysis |
| title_full_unstemmed | A fast correction approach to tensor robust principal component analysis |
| title_short | A fast correction approach to tensor robust principal component analysis |
| title_sort | fast correction approach to tensor robust principal component analysis |
| topic | Engineering Tensor nuclear norm Tensor singular value decomposition |
| url | https://hdl.handle.net/10356/180347 |
| work_keys_str_mv | AT zhangzhechen afastcorrectionapproachtotensorrobustprincipalcomponentanalysis AT liusanyang afastcorrectionapproachtotensorrobustprincipalcomponentanalysis AT linzhiping afastcorrectionapproachtotensorrobustprincipalcomponentanalysis AT xuejize afastcorrectionapproachtotensorrobustprincipalcomponentanalysis AT liulixia afastcorrectionapproachtotensorrobustprincipalcomponentanalysis AT zhangzhechen fastcorrectionapproachtotensorrobustprincipalcomponentanalysis AT liusanyang fastcorrectionapproachtotensorrobustprincipalcomponentanalysis AT linzhiping fastcorrectionapproachtotensorrobustprincipalcomponentanalysis AT xuejize fastcorrectionapproachtotensorrobustprincipalcomponentanalysis AT liulixia fastcorrectionapproachtotensorrobustprincipalcomponentanalysis |