A simplified view of first order methods for optimization

Marc Teboulle*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

We discuss the foundational role of the proximal framework in the development and analysis of some iconic first order optimization algorithms, with a focus on non-Euclidean proximal distances of Bregman type, which are central to the analysis of many other fundamental first order minimization relatives. We stress simplification and unification by highlighting self-contained elementary proof-patterns to obtain convergence rate and global convergence both in the convex and the nonconvex settings, which in turn also allows to present some novel results.

Original languageEnglish
Pages (from-to)67-96
Number of pages30
JournalMathematical Programming
Volume170
Issue number1
DOIs
StatePublished - 1 Jul 2018

Keywords

  • Convex and nonconvex minimization
  • Descent Lemma
  • First order algorithms
  • Kurdyka–Łosiajewicz property
  • Non-Euclidean Bregman distance
  • Proximal framework

Fingerprint

Dive into the research topics of 'A simplified view of first order methods for optimization'. Together they form a unique fingerprint.

Cite this