Convergences Rates of Proximal Gradient Methods via the Convex Conjugate

David Gutman, Javier Pena

Research output: Contribution to journalArticle

Abstract

We give a novel proof of the ${{\mathcal O}}(1/k)$ and ${{\mathcal O}}(1/k^2)$ 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
JournalSIAM Journal on Optimization
DOIs
StatePublished - Jan 17 2019

Fingerprint Dive into the research topics of 'Convergences Rates of Proximal Gradient Methods via the Convex Conjugate'. Together they form a unique fingerprint.

  • Cite this