Accelerated forward-backward and Douglas-Rachford splitting dynamics
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910711870914560 |
|---|---|
| author | Ozaslan, Ibrahim K. Jovanović, Mihailo R. |
| author_facet | Ozaslan, Ibrahim K. Jovanović, Mihailo R. |
| contents | We examine convergence properties of continuous-time variants of accelerated Forward-Backward (FB) and Douglas-Rachford (DR) splitting algorithms for nonsmooth composite optimization problems. When the objective function is given by the sum of a quadratic and a nonsmooth term, we establish accelerated sublinear and exponential convergence rates for convex and strongly convex problems, respectively. Moreover, for FB splitting dynamics, we demonstrate that accelerated exponential convergence rate carries over to general strongly convex problems. In our Lyapunov-based analysis we exploit the variable-metric gradient interpretations of FB and DR splittings to obtain smooth Lyapunov functions that allow us to establish accelerated convergence rates. We provide computational experiments to demonstrate the merits and the effectiveness of our analysis. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_20620 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Accelerated forward-backward and Douglas-Rachford splitting dynamics Ozaslan, Ibrahim K. Jovanović, Mihailo R. Optimization and Control Machine Learning Systems and Control We examine convergence properties of continuous-time variants of accelerated Forward-Backward (FB) and Douglas-Rachford (DR) splitting algorithms for nonsmooth composite optimization problems. When the objective function is given by the sum of a quadratic and a nonsmooth term, we establish accelerated sublinear and exponential convergence rates for convex and strongly convex problems, respectively. Moreover, for FB splitting dynamics, we demonstrate that accelerated exponential convergence rate carries over to general strongly convex problems. In our Lyapunov-based analysis we exploit the variable-metric gradient interpretations of FB and DR splittings to obtain smooth Lyapunov functions that allow us to establish accelerated convergence rates. We provide computational experiments to demonstrate the merits and the effectiveness of our analysis. |
| title | Accelerated forward-backward and Douglas-Rachford splitting dynamics |
| topic | Optimization and Control Machine Learning Systems and Control |
| url | https://arxiv.org/abs/2407.20620 |