A New Exact Worst-Case Linear Convergence Rate of the Proximal Gradient Method

arXiv1902.09181MaRDI QIDQ6314564FDOQ6314564

Authors: Xiaoya Zhang, Hui Zhang 

Publication date: 25 February 2019

Abstract: In this note, we establish a new exact worst-case linear convergence rate of the proximal gradient method in terms of the proximal gradient norm, which complements the recent results in [1] and implies a refined descent lemma.descent lemma. Based on the new lemma, we improve the linear convergence rate of the objective function accuracy under the Polyak-Lojasiewicz inequality.

Mathematics Subject Classification ID

Quadratic programming (90C20) Convex programming (90C25) Semidefinite programming (90C22)

This page was built for publication: A New Exact Worst-Case Linear Convergence Rate of the Proximal Gradient Method

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6314564)