Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2604.18325 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913047836098560 |
|---|---|
| author | Wang, Lei Chen, Xiaojun |
| author_facet | Wang, Lei Chen, Xiaojun |
| contents | We study a class of optimization problems on Riemannian manifolds, where the objective function consists of a smooth term and quasi-norm type penalties with exponent $p \in (0, 1]$. The essential difficulty lies in the fact that the objective function may not be locally Lipschitz continuous, which places this type of problems beyond the reach of existing Riemannian techniques. To overcome this obstacle, this paper constructs a general smoothing framework and establishes fundamental properties for developing efficient algorithms. In particular, we propose a smoothing Riemannian gradient algorithm equipped with a smoothing-aware AdaGrad-type stepsize rule. Its global convergence is demonstrated together with an iteration complexity of $O (ε^{p - 4})$, which includes the best available iteration complexity of $O (ε^{- 3})$ for Lipschitz problems with $p = 1$ as a special case. To the best of our knowledge, this is the first complexity result for non-Lipschitz optimization on Riemannian manifolds. Preliminary numerical experiments corroborate the practical efficiency of the proposed approach in real-world applications arsing from machine learning and data science. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_18325 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | An Adaptive Smoothing Algorithm for Non-Lipschitz Optimization on Manifolds with Complexity Guarantees Wang, Lei Chen, Xiaojun Optimization and Control We study a class of optimization problems on Riemannian manifolds, where the objective function consists of a smooth term and quasi-norm type penalties with exponent $p \in (0, 1]$. The essential difficulty lies in the fact that the objective function may not be locally Lipschitz continuous, which places this type of problems beyond the reach of existing Riemannian techniques. To overcome this obstacle, this paper constructs a general smoothing framework and establishes fundamental properties for developing efficient algorithms. In particular, we propose a smoothing Riemannian gradient algorithm equipped with a smoothing-aware AdaGrad-type stepsize rule. Its global convergence is demonstrated together with an iteration complexity of $O (ε^{p - 4})$, which includes the best available iteration complexity of $O (ε^{- 3})$ for Lipschitz problems with $p = 1$ as a special case. To the best of our knowledge, this is the first complexity result for non-Lipschitz optimization on Riemannian manifolds. Preliminary numerical experiments corroborate the practical efficiency of the proposed approach in real-world applications arsing from machine learning and data science. |
| title | An Adaptive Smoothing Algorithm for Non-Lipschitz Optimization on Manifolds with Complexity Guarantees |
| topic | Optimization and Control |
| url | https://arxiv.org/abs/2604.18325 |