Structured Gradient Descent for Fast Robust Low-Rank Hankel Matrix Completion
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2022
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909580500402176 |
|---|---|
| author | Cai, HanQin Cai, Jian-Feng You, Juntao |
| author_facet | Cai, HanQin Cai, Jian-Feng You, Juntao |
| contents | We study the robust matrix completion problem for the low-rank Hankel matrix, which detects the sparse corruptions caused by extreme outliers while we try to recover the original Hankel matrix from the partial observation. In this paper, we explore the convenient Hankel structure and propose a novel non-convex algorithm, coined Hankel Structured Gradient Descent (HSGD), for large-scale robust Hankel matrix completion problems. HSGD is highly computing- and sample-efficient compared to the state-of-the-arts. The recovery guarantee with a linear convergence rate has been established for HSGD under some mild assumptions. The empirical advantages of HSGD are verified on both synthetic datasets and real-world nuclear magnetic resonance signals. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2204_03316 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Structured Gradient Descent for Fast Robust Low-Rank Hankel Matrix Completion Cai, HanQin Cai, Jian-Feng You, Juntao Information Theory Optimization and Control We study the robust matrix completion problem for the low-rank Hankel matrix, which detects the sparse corruptions caused by extreme outliers while we try to recover the original Hankel matrix from the partial observation. In this paper, we explore the convenient Hankel structure and propose a novel non-convex algorithm, coined Hankel Structured Gradient Descent (HSGD), for large-scale robust Hankel matrix completion problems. HSGD is highly computing- and sample-efficient compared to the state-of-the-arts. The recovery guarantee with a linear convergence rate has been established for HSGD under some mild assumptions. The empirical advantages of HSGD are verified on both synthetic datasets and real-world nuclear magnetic resonance signals. |
| title | Structured Gradient Descent for Fast Robust Low-Rank Hankel Matrix Completion |
| topic | Information Theory Optimization and Control |
| url | https://arxiv.org/abs/2204.03316 |