A Simple Linear Convergence Analysis of the Point-SAGA Algorithm
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_ | 1866929366265495552 |
|---|---|
| author | Condat, Laurent Richtárik, Peter |
| author_facet | Condat, Laurent Richtárik, Peter |
| contents | Point-SAGA is a randomized algorithm for minimizing a sum of convex functions using their proximity operators (proxs), proposed by Defazio (2016). At every iteration, the prox of only one randomly chosen function is called. We generalize the algorithm to any number of prox calls per iteration, not only one, and propose a simple proof of linear convergence when the functions are smooth and strongly convex. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_19951 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Simple Linear Convergence Analysis of the Point-SAGA Algorithm Condat, Laurent Richtárik, Peter Optimization and Control Point-SAGA is a randomized algorithm for minimizing a sum of convex functions using their proximity operators (proxs), proposed by Defazio (2016). At every iteration, the prox of only one randomly chosen function is called. We generalize the algorithm to any number of prox calls per iteration, not only one, and propose a simple proof of linear convergence when the functions are smooth and strongly convex. |
| title | A Simple Linear Convergence Analysis of the Point-SAGA Algorithm |
| topic | Optimization and Control |
| url | https://arxiv.org/abs/2405.19951 |