Convergence rates of proximal gradient methods via the convex conjugate

David H. Gutman, Javier F. Pena

Research output: Contribution to journalArticle

Abstract

We give a novel proof of the O(1/k) and O(1/k 2 ) convergence rates of the proximal gradient and accelerated proximal gradient methods for composite convex minimization. The crux of the new proof is an upper bound constructed via the convex conjugate of the objective function.

Original languageEnglish
Pages (from-to)162-174
Number of pages13
JournalSIAM Journal on Optimization
Volume29
Issue number1
DOIs
StatePublished - 2019

Keywords

  • Acceleration
  • Convex conjugate
  • Proximal gradient

Fingerprint Dive into the research topics of 'Convergence rates of proximal gradient methods via the convex conjugate'. Together they form a unique fingerprint.

Cite this