EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Projected Gradient Methods with Momentum

Matteo Lapucci, Giampaolo Liuzzi, Stefano Lucidi, Marco Sciandrone, Diego Scuppa

Journal of Optimization Theory and Applications · 2026-07 · 210 (1)

DOI: 10.1007/s10957-026-03054-7 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Optimization Theory and Applications, online erschienen am 03.07.2026. Verfasst von Matteo Lapucci und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Università degli Studi di Roma La Sapienza.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We focus on the optimization problem with smooth, possibly nonconvex objectives and a convex constraint set for which the Euclidean projection operation is practically available. Focusing on this setting, we carry out a general convergence and complexity analysis for algorithmic frameworks. Consequently, we discuss theoretically sound strategies to integrate momentum information within classical projected gradient-type algorithms. One of these approaches is then developed in detail, up to the definition of a tailored algorithm with both theoretical guarantees and reasonable per-iteration cost. The proposed method is finally shown to outperform the standard (spectral) projected gradient method in two different experimental benchmarks, indicating that the addition of momentum terms is as beneficial in the constrained setting as it is in the unconstrained scenario.

Förderung

  • Università degli Studi di Roma La Sapienza

Zitieren

APA

Lapucci, M., Liuzzi, G., Lucidi, S., Sciandrone, M., & Scuppa, D. (2026). Projected Gradient Methods with Momentum. Journal of Optimization Theory and Applications, 210(1). https://doi.org/10.1007/s10957-026-03054-7

Vancouver

Lapucci M, Liuzzi G, Lucidi S, Sciandrone M, Scuppa D. Projected Gradient Methods with Momentum. Journal of Optimization Theory and Applications. 2026;210(1). doi:10.1007/s10957-026-03054-7

BibTeX
@article{Lapucci2026,
  author = {Lapucci, Matteo and Liuzzi, Giampaolo and Lucidi, Stefano and Sciandrone, Marco and Scuppa, Diego},
  title = {Projected Gradient Methods with Momentum},
  journal = {Journal of Optimization Theory and Applications},
  year = {2026},
  volume = {210},
  number = {1},
  doi = {10.1007/s10957-026-03054-7}
}
Kostenlos starten →