Nonsmooth Riemannian optimization with inexact manifold primitives via bundle methods
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915968066781184 |
|---|---|
| author | Díaz, Mateo Grimmer, Benjamin McPherson, Ian |
| author_facet | Díaz, Mateo Grimmer, Benjamin McPherson, Ian |
| contents | Optimization on Hadamard manifolds -- the natural Riemannian setting for globally geodesically convex problems -- relies on exponential maps to retract tangent vectors and parallel transport to connect tangent spaces across the manifold. These primitives are often computationally expensive, leading software packages to rely on approximations: first-order retractions and vector transports. However, existing results for optimization on Hadamard manifolds either require exact primitives or lack non-asymptotic rates. We bridge this gap by introducing a proximal bundle method for nonsmooth geodesically convex optimization and establishing the first oracle-complexity bounds that rely only on subgradients and inexact primitives. We obtain sublinear rates for general objectives and optimal linear convergence under sharp function growth. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_27078 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Nonsmooth Riemannian optimization with inexact manifold primitives via bundle methods Díaz, Mateo Grimmer, Benjamin McPherson, Ian Optimization and Control Primary: 90C26. Secondary: 49J52, 49M37, 53C99 Optimization on Hadamard manifolds -- the natural Riemannian setting for globally geodesically convex problems -- relies on exponential maps to retract tangent vectors and parallel transport to connect tangent spaces across the manifold. These primitives are often computationally expensive, leading software packages to rely on approximations: first-order retractions and vector transports. However, existing results for optimization on Hadamard manifolds either require exact primitives or lack non-asymptotic rates. We bridge this gap by introducing a proximal bundle method for nonsmooth geodesically convex optimization and establishing the first oracle-complexity bounds that rely only on subgradients and inexact primitives. We obtain sublinear rates for general objectives and optimal linear convergence under sharp function growth. |
| title | Nonsmooth Riemannian optimization with inexact manifold primitives via bundle methods |
| topic | Optimization and Control Primary: 90C26. Secondary: 49J52, 49M37, 53C99 |
| url | https://arxiv.org/abs/2604.27078 |