One to beat them all: "RYU" -- a unifying framework for the construction of safe balls
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918146664824832 |
|---|---|
| author | Tran, Thu-Le Elvira, Clément Dang, Hong-Phuong Herzet, Cédric |
| author_facet | Tran, Thu-Le Elvira, Clément Dang, Hong-Phuong Herzet, Cédric |
| contents | In this paper, we present a new framework, called "RYU" for constructing "safe" regions -- specifically, bounded sets that are guaranteed to contain the dual solution of a target optimization problem. Our framework applies to the standard case where the objective function is composed of two components: a closed, proper, convex function with Lipschitz-smooth gradient and another closed, proper, convex function. We show that the RYU framework not only encompasses but also improves upon the state-of-the-art methods proposed over the past decade for this class of optimization problems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_00640 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | One to beat them all: "RYU" -- a unifying framework for the construction of safe balls Tran, Thu-Le Elvira, Clément Dang, Hong-Phuong Herzet, Cédric Optimization and Control Machine Learning In this paper, we present a new framework, called "RYU" for constructing "safe" regions -- specifically, bounded sets that are guaranteed to contain the dual solution of a target optimization problem. Our framework applies to the standard case where the objective function is composed of two components: a closed, proper, convex function with Lipschitz-smooth gradient and another closed, proper, convex function. We show that the RYU framework not only encompasses but also improves upon the state-of-the-art methods proposed over the past decade for this class of optimization problems. |
| title | One to beat them all: "RYU" -- a unifying framework for the construction of safe balls |
| topic | Optimization and Control Machine Learning |
| url | https://arxiv.org/abs/2312.00640 |