On the Convergence of Weak Greedy Algorithm for a Class of Non-Smooth Optimization Problemsin Banach Spaces
Algorithms · 17.03.2026 · 19 (3) · 227
DOI: 10.3390/a19030227 ↗Kurz gefasst
Fachartikel in der Zeitschrift Algorithms, online erschienen am 17.03.2026. Verfasst von Sergei Sidorov. Die Arbeit nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Science and Higher Education of the Russian Federation.
Abstract (Originalsprache)
The paper discusses a greedy algorithm that can be used to solve non-smooth optimization problems in which its objective function can be represented as a minimum of a compactly parameterized family of uniformly smooth functions. The algorithm guarantees a sparse solution by adding one atom from the dictionary to the solution at each iteration. The algorithm employs a gradient greedy step that maximizes a linear functional using gradient information from the previous iteration. However, the algorithm is considered “weak” because it only solves the linear subproblems approximately. By employing the duality gap evaluated at each gradient-greedy step, the paper proves convergence of the algorithm to Clarke stationary points. Explicit upper bounds on the duality gap are derived, yielding a quantitative measure of proximity to stationarity and establishing the corresponding rates of convergence.
Förderung
- Ministry of Science and Higher Education of the Russian Federation
Zitieren
APA
Sidorov, S. (2026). On the Convergence of Weak Greedy Algorithm for a Class of Non-Smooth Optimization Problemsin Banach Spaces. Algorithms, 19(3), 227. https://doi.org/10.3390/a19030227
Vancouver
Sidorov S. On the Convergence of Weak Greedy Algorithm for a Class of Non-Smooth Optimization Problemsin Banach Spaces. Algorithms. 2026;19(3):227. doi:10.3390/a19030227
BibTeX
@article{Sidorov2026,
author = {Sidorov, Sergei},
title = {On the Convergence of Weak Greedy Algorithm for a Class of Non-Smooth Optimization Problemsin Banach Spaces},
journal = {Algorithms},
year = {2026},
volume = {19},
number = {3},
pages = {227},
doi = {10.3390/a19030227}
}
EUVIMED