EUVIMEDSkopri EUVIMED
Crossref

Quadratic error bound of the smoothed gap and the restarted averaged primal-dual hybrid gradient

Olivier Fercoq

Open Journal of Mathematical Optimization · 2023

DOI: 10.5802/ojmo.26 ↗

At a glance

Journal article in Open Journal of Mathematical Optimization, 2023. Written by Olivier Fercoq. Cited 5 times so far (Crossref); 32 references.

AstrattDettalji biblijografiċiCiteRelated studies

Abstract (original language)

We study the linear convergence of the primal-dual hybrid gradient method. After a review of current analyses, we show that they do not explain properly the behavior of the algorithm, even on the most simple problems. We thus introduce the quadratic error bound of the smoothed gap, a new regularity assumption that holds for a wide class of optimization problems. Equipped with this tool, we manage to prove tighter convergence rates. Then, we show that averaging and restarting the primal-dual hybrid gradient allows us to leverage better the regularity constant. Numerical experiments on linear and quadratic programs, ridge regression and image denoising illustrate the findings of the paper.

Cite

APA

Fercoq, O. (2023). Quadratic error bound of the smoothed gap and the restarted averaged primal-dual hybrid gradient. Open Journal of Mathematical Optimization. https://doi.org/10.5802/ojmo.26

Vancouver

Fercoq O. Quadratic error bound of the smoothed gap and the restarted averaged primal-dual hybrid gradient. Open Journal of Mathematical Optimization. 2023. doi:10.5802/ojmo.26

BibTeX
@article{Fercoq2023,
  author = {Fercoq, Olivier},
  title = {Quadratic error bound of the smoothed gap and the restarted averaged primal-dual hybrid gradient},
  journal = {Open Journal of Mathematical Optimization},
  year = {2023},
  doi = {10.5802/ojmo.26}
}
Start for free →