Beyond Low-rankness: Guaranteed Matrix Recovery via Modified Nuclear Norm
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908464504111104 |
|---|---|
| author | Peng, Jiangjun Luo, Yisi Cao, Xiangyong Xu, Shuang Meng, Deyu |
| author_facet | Peng, Jiangjun Luo, Yisi Cao, Xiangyong Xu, Shuang Meng, Deyu |
| contents | The nuclear norm (NN) has been widely explored in matrix recovery problems, such as Robust PCA and matrix completion, leveraging the inherent global low-rank structure of the data. In this study, we introduce a new modified nuclear norm (MNN) framework, where the MNN family norms are defined by adopting suitable transformations and performing the NN on the transformed matrix. The MNN framework offers two main advantages: (1) it jointly captures both local information and global low-rankness without requiring trade-off parameter tuning; (2) Under mild assumptions on the transformation, we provided exact theoretical recovery guarantees for both Robust PCA and MC tasks-an achievement not shared by existing methods that combine local and global information. Thanks to its general and flexible design, MNN can accommodate various proven transformations, enabling a unified and effective approach to structured low-rank recovery. Extensive experiments demonstrate the effectiveness of our method. Code and supplementary material are available at https://github.com/andrew-pengjj/modified_nuclear_norm. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_18327 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Beyond Low-rankness: Guaranteed Matrix Recovery via Modified Nuclear Norm Peng, Jiangjun Luo, Yisi Cao, Xiangyong Xu, Shuang Meng, Deyu Computer Vision and Pattern Recognition The nuclear norm (NN) has been widely explored in matrix recovery problems, such as Robust PCA and matrix completion, leveraging the inherent global low-rank structure of the data. In this study, we introduce a new modified nuclear norm (MNN) framework, where the MNN family norms are defined by adopting suitable transformations and performing the NN on the transformed matrix. The MNN framework offers two main advantages: (1) it jointly captures both local information and global low-rankness without requiring trade-off parameter tuning; (2) Under mild assumptions on the transformation, we provided exact theoretical recovery guarantees for both Robust PCA and MC tasks-an achievement not shared by existing methods that combine local and global information. Thanks to its general and flexible design, MNN can accommodate various proven transformations, enabling a unified and effective approach to structured low-rank recovery. Extensive experiments demonstrate the effectiveness of our method. Code and supplementary material are available at https://github.com/andrew-pengjj/modified_nuclear_norm. |
| title | Beyond Low-rankness: Guaranteed Matrix Recovery via Modified Nuclear Norm |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.18327 |