On the Robustness of Cross-Concentrated Sampling for Matrix Completion
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912330039689216 |
|---|---|
| author | Cai, HanQin Huang, Longxiu Kundu, Chandra Su, Bowen |
| author_facet | Cai, HanQin Huang, Longxiu Kundu, Chandra Su, Bowen |
| contents | Matrix completion is one of the crucial tools in modern data science research. Recently, a novel sampling model for matrix completion coined cross-concentrated sampling (CCS) has caught much attention. However, the robustness of the CCS model against sparse outliers remains unclear in the existing studies. In this paper, we aim to answer this question by exploring a novel Robust CCS Completion problem. A highly efficient non-convex iterative algorithm, dubbed Robust CUR Completion (RCURC), is proposed. The empirical performance of the proposed algorithm, in terms of both efficiency and robustness, is verified in synthetic and real datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_15566 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | On the Robustness of Cross-Concentrated Sampling for Matrix Completion Cai, HanQin Huang, Longxiu Kundu, Chandra Su, Bowen Machine Learning Information Theory Optimization and Control Matrix completion is one of the crucial tools in modern data science research. Recently, a novel sampling model for matrix completion coined cross-concentrated sampling (CCS) has caught much attention. However, the robustness of the CCS model against sparse outliers remains unclear in the existing studies. In this paper, we aim to answer this question by exploring a novel Robust CCS Completion problem. A highly efficient non-convex iterative algorithm, dubbed Robust CUR Completion (RCURC), is proposed. The empirical performance of the proposed algorithm, in terms of both efficiency and robustness, is verified in synthetic and real datasets. |
| title | On the Robustness of Cross-Concentrated Sampling for Matrix Completion |
| topic | Machine Learning Information Theory Optimization and Control |
| url | https://arxiv.org/abs/2401.15566 |