Repository logo

Infoscience

  • English
  • French
Log In
Logo EPFL, École polytechnique fédérale de Lausanne

Infoscience

  • English
  • French
Log In
  1. Home
  2. Academic and Research Output
  3. Journal articles
  4. A Smooth Primal-Dual Optimization Framework for Nonsmooth Composite Convex Minimization
 
research article

A Smooth Primal-Dual Optimization Framework for Nonsmooth Composite Convex Minimization

Tran Dinh, Quoc  
•
Fercoq, Olivier
•
Cevher, Volkan  orcid-logo
January 11, 2018
SIAM Journal on Optimization

We propose a new and low per-iteration complexity first-order primal-dual optimization framework for a convex optimization template with broad applications. Our analysis relies on a novel combination of three classic ideas applied to the primal-dual gap function: smoothing, acceleration, and homotopy. The algorithms due to the new approach achieve the best-known convergence rate results, in particular when the template consists of only nonsmooth functions. We also outline a restart strategy for the acceleration to significantly enhance the practical performance. We demonstrate relations with the augmented Lagrangian method and show how to exploit the strongly convex objectives with rigorous convergence rate guarantees. We provide representative examples to illustrate that the new methods can outperform the state of the art, including Chambolle--Pock, and the alternating direction method-of-multipliers algorithms. We also compare our algorithms with the well-known Nesterov smoothing method.

  • Files
  • Details
  • Metrics
Loading...
Thumbnail Image
Name

SmoothPD_2018.pdf

Access type

openaccess

Size

2.68 MB

Format

Adobe PDF

Checksum (MD5)

af6fe35679491e542998b09d9fbdc71a

Logo EPFL, École polytechnique fédérale de Lausanne
  • Contact
  • infoscience@epfl.ch

  • Follow us on Facebook
  • Follow us on Instagram
  • Follow us on LinkedIn
  • Follow us on X
  • Follow us on Youtube
AccessibilityLegal noticePrivacy policyCookie settingsEnd User AgreementGet helpFeedback

Infoscience is a service managed and provided by the Library and IT Services of EPFL. © EPFL, tous droits réservés