Projected Gradient Methods with Momentum
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917426990415872 |
|---|---|
| author | Lapucci, Matteo Liuzzi, Giampaolo Lucidi, Stefano Sciandrone, Marco Scuppa, Diego |
| author_facet | Lapucci, Matteo Liuzzi, Giampaolo Lucidi, Stefano Sciandrone, Marco Scuppa, Diego |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_16683 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Projected Gradient Methods with Momentum Lapucci, Matteo Liuzzi, Giampaolo Lucidi, Stefano Sciandrone, Marco Scuppa, Diego Optimization and Control 90C29, 90C26, 90C60 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. |
| title | Projected Gradient Methods with Momentum |
| topic | Optimization and Control 90C29, 90C26, 90C60 |
| url | https://arxiv.org/abs/2601.16683 |