Alberto De Marchi - Proximal gradient methods beyond monotony

jnsao:10290 - Journal of Nonsmooth Analysis and Optimization, June 2, 2023, Volume 4 - https://doi.org/10.46298/jnsao-2023-10290
Proximal gradient methods beyond monotonyArticle

Authors: Alberto De Marchi 1

We address composite optimization problems, which consist in minimizing the sum of a smooth and a merely lower semicontinuous function, without any convexity assumptions. Numerical solutions of these problems can be obtained by proximal gradient methods, which often rely on a line search procedure as globalization mechanism. We consider an adaptive nonmonotone proximal gradient scheme based on an averaged merit function and establish asymptotic convergence guarantees under weak assumptions, delivering results on par with the monotone strategy. Global worst-case rates for the iterates and a stationarity measure are also derived. Finally, a numerical example indicates the potential of nonmonotonicity and spectral approximations.


Volume: Volume 4
Section: Original research articles
Published on: June 2, 2023
Accepted on: May 25, 2023
Submitted on: November 10, 2022
Keywords: Mathematics - Optimization and Control

Consultation statistics

This page has been seen 386 times.
This article's PDF has been downloaded 428 times.