Discrete-time gradient flows in Gromov hyperbolic spaces
Fuente:
arXiv
Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2022
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929692745924608 |
|---|---|
| author | Ohta, Shin-ichi |
| author_facet | Ohta, Shin-ichi |
| contents | We investigate fundamental properties of the proximal point algorithm for Lipschitz convex functions on (proper, geodesic) Gromov hyperbolic spaces. We show that the proximal point algorithm from an arbitrary initial point can find a point close to a minimizer of the function. Moreover, we establish contraction estimates (akin to trees) for the proximal (resolvent) operator. Our results can be applied to small perturbations of trees. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2205_03156 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Discrete-time gradient flows in Gromov hyperbolic spaces Ohta, Shin-ichi Optimization and Control Metric Geometry We investigate fundamental properties of the proximal point algorithm for Lipschitz convex functions on (proper, geodesic) Gromov hyperbolic spaces. We show that the proximal point algorithm from an arbitrary initial point can find a point close to a minimizer of the function. Moreover, we establish contraction estimates (akin to trees) for the proximal (resolvent) operator. Our results can be applied to small perturbations of trees. |
| title | Discrete-time gradient flows in Gromov hyperbolic spaces |
| topic | Optimization and Control Metric Geometry |
| url | https://arxiv.org/abs/2205.03156 |