One to beat them all: 'RYU' – a unifying framework for the construction of safe balls
Gespeichert in:
| Titel: | One to beat them all: 'RYU' – a unifying framework for the construction of safe balls |
|---|---|
| Autoren: | Tran, Thu-Le, Elvira, Clément, Dang, Hong-Phuong, Herzet, Cédric |
| Weitere Verfasser: | Elvira, Clément |
| Quelle: | Open Journal of Mathematical Optimization. 6:1-16 |
| Publication Status: | Preprint |
| Verlagsinformationen: | Cellule MathDoc/Centre Mersenne, 2025. |
| Publikationsjahr: | 2025 |
| Schlagwörter: | Machine Learning, FOS: Computer and information sciences, Optimization and Control (math.OC), Optimization and Control, FOS: Mathematics, safe regions, [MATH.MATH-OC] Mathematics [math]/Optimization and Control [math.OC], Machine Learning (stat.ML), [INFO.INFO-LG] Computer Science [cs]/Machine Learning [cs.LG], Convex optimization, screening rules, Machine Learning (cs.LG) |
| Beschreibung: | In this paper, we present a new framework, called “RYU”, for constructing “safe” regions – specifically, 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. |
| Publikationsart: | Article |
| Dateibeschreibung: | application/pdf |
| Sprache: | English |
| ISSN: | 2777-5860 |
| DOI: | 10.5802/ojmo.45 |
| DOI: | 10.48550/arxiv.2312.00640 |
| Zugangs-URL: | http://arxiv.org/abs/2312.00640 https://hal.science/hal-04318380v3 https://doi.org/10.5802/ojmo.45 https://hal.science/hal-04318380v3/document |
| Rights: | CC BY arXiv Non-Exclusive Distribution |
| Dokumentencode: | edsair.doi.dedup.....24622811e80ece2a465f30cc26f450be |
| Datenbank: | OpenAIRE |
Full Text Finder 
Nájsť tento článok vo Web of Science | Abstract: | In this paper, we present a new framework, called “RYU”, for constructing “safe” regions – specifically, 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. |
|---|---|
| ISSN: | 27775860 |
| DOI: | 10.5802/ojmo.45 |