A Framework for Bilevel Optimization on Riemannian Manifolds
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915002072432640 |
|---|---|
| author | Han, Andi Mishra, Bamdev Jawanpuria, Pratik Takeda, Akiko |
| author_facet | Han, Andi Mishra, Bamdev Jawanpuria, Pratik Takeda, Akiko |
| contents | Bilevel optimization has gained prominence in various applications. In this study, we introduce a framework for solving bilevel optimization problems, where the variables in both the lower and upper levels are constrained on Riemannian manifolds. We present several hypergradient estimation strategies on manifolds and analyze their estimation errors. Furthermore, we provide comprehensive convergence and complexity analyses for the proposed hypergradient descent algorithm on manifolds. We also extend our framework to encompass stochastic bilevel optimization and incorporate the use of general retraction. The efficacy of the proposed framework is demonstrated through several applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_03883 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Framework for Bilevel Optimization on Riemannian Manifolds Han, Andi Mishra, Bamdev Jawanpuria, Pratik Takeda, Akiko Optimization and Control Machine Learning Bilevel optimization has gained prominence in various applications. In this study, we introduce a framework for solving bilevel optimization problems, where the variables in both the lower and upper levels are constrained on Riemannian manifolds. We present several hypergradient estimation strategies on manifolds and analyze their estimation errors. Furthermore, we provide comprehensive convergence and complexity analyses for the proposed hypergradient descent algorithm on manifolds. We also extend our framework to encompass stochastic bilevel optimization and incorporate the use of general retraction. The efficacy of the proposed framework is demonstrated through several applications. |
| title | A Framework for Bilevel Optimization on Riemannian Manifolds |
| topic | Optimization and Control Machine Learning |
| url | https://arxiv.org/abs/2402.03883 |