Nonlinear Eigen-approach ADMM for Sparse Optimization on Stiefel Manifold
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916272998973440 |
|---|---|
| author | Wang, Jiawei Li, Rencang Da Xu, Richard Yi |
| author_facet | Wang, Jiawei Li, Rencang Da Xu, Richard Yi |
| contents | With the growing interest and applications in machine learning and data science, finding an efficient method to sparse analysis the high-dimensional data and optimizing a dimension reduction model to extract lower dimensional features has becoming more and more important. Orthogonal constraints (Stiefel manifold) is a commonly met constraint in these applications, and the sparsity is usually enforced through the element-wise L1 norm. Many applications can be found on optimization over Stiefel manifold within the area of physics and machine learning. In this paper, we propose a novel idea by tackling the Stiefel manifold through an nonlinear eigen-approach by first using ADMM to split the problem into smooth optimization over manifold and convex non-smooth optimization, and then transforming the former into the form of nonlinear eigenvalue problem with eigenvector dependency (NEPv) which is solved by self-consistent field (SCF) iteration, and the latter can be found to have an closed-form solution through proximal gradient. Compared with existing methods, our proposed algorithm takes the advantage of specific structure of the objective function, and has efficient convergence results under mild assumptions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_01885 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Nonlinear Eigen-approach ADMM for Sparse Optimization on Stiefel Manifold Wang, Jiawei Li, Rencang Da Xu, Richard Yi Optimization and Control With the growing interest and applications in machine learning and data science, finding an efficient method to sparse analysis the high-dimensional data and optimizing a dimension reduction model to extract lower dimensional features has becoming more and more important. Orthogonal constraints (Stiefel manifold) is a commonly met constraint in these applications, and the sparsity is usually enforced through the element-wise L1 norm. Many applications can be found on optimization over Stiefel manifold within the area of physics and machine learning. In this paper, we propose a novel idea by tackling the Stiefel manifold through an nonlinear eigen-approach by first using ADMM to split the problem into smooth optimization over manifold and convex non-smooth optimization, and then transforming the former into the form of nonlinear eigenvalue problem with eigenvector dependency (NEPv) which is solved by self-consistent field (SCF) iteration, and the latter can be found to have an closed-form solution through proximal gradient. Compared with existing methods, our proposed algorithm takes the advantage of specific structure of the objective function, and has efficient convergence results under mild assumptions. |
| title | Nonlinear Eigen-approach ADMM for Sparse Optimization on Stiefel Manifold |
| topic | Optimization and Control |
| url | https://arxiv.org/abs/2406.01885 |