Proximal methods for structured nonsmooth optimization over Riemannian submanifolds
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912689334255616 |
|---|---|
| author | Li, Qia Zhang, Na Feng, Junyu Yan, Hanwei |
| author_facet | Li, Qia Zhang, Na Feng, Junyu Yan, Hanwei |
| contents | In this paper, we consider a class of structured nonsmooth optimization problems over an embedded submanifold of a Euclidean space, where the first part of the objective is the sum of a difference-of-convex (DC) function and a smooth function, while the remaining part is a weakly convex function over a smooth function. This model problem has many important applications in machine learning and scientific computing, for example, the sparse Fisher discriminant analysis. We propose a manifold proximal-gradient-subgradient algorithm (MPGSA) and show that under mild conditions any accumulation point of the solution sequence generated by it is a critical point of the underlying problem. By assuming the Kurdyka-Łojasiewicz property of an auxiliary function, we further establish the convergence of the full sequence generated by MPGSA under some suitable conditions. When the second component of the DC function involved is the maximum of finite continuously differentiable convex functions, we also propose an enhanced MPGSA with guaranteed subsequential convergence to a lifted B-stationary points of the optimization problem. Finally, some preliminary numerical experiments are conducted to illustrate the efficiency of the proposed algorithms. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_15776 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Proximal methods for structured nonsmooth optimization over Riemannian submanifolds Li, Qia Zhang, Na Feng, Junyu Yan, Hanwei Optimization and Control 90C26, 90C30, 65K05 In this paper, we consider a class of structured nonsmooth optimization problems over an embedded submanifold of a Euclidean space, where the first part of the objective is the sum of a difference-of-convex (DC) function and a smooth function, while the remaining part is a weakly convex function over a smooth function. This model problem has many important applications in machine learning and scientific computing, for example, the sparse Fisher discriminant analysis. We propose a manifold proximal-gradient-subgradient algorithm (MPGSA) and show that under mild conditions any accumulation point of the solution sequence generated by it is a critical point of the underlying problem. By assuming the Kurdyka-Łojasiewicz property of an auxiliary function, we further establish the convergence of the full sequence generated by MPGSA under some suitable conditions. When the second component of the DC function involved is the maximum of finite continuously differentiable convex functions, we also propose an enhanced MPGSA with guaranteed subsequential convergence to a lifted B-stationary points of the optimization problem. Finally, some preliminary numerical experiments are conducted to illustrate the efficiency of the proposed algorithms. |
| title | Proximal methods for structured nonsmooth optimization over Riemannian submanifolds |
| topic | Optimization and Control 90C26, 90C30, 65K05 |
| url | https://arxiv.org/abs/2411.15776 |