Alberto De Marchi ; Patrick Mehlitz - Local properties and augmented Lagrangians in fully nonconvex composite optimization

jnsao:12235 - Journal of Nonsmooth Analysis and Optimization, May 16, 2024, Volume 5 - https://doi.org/10.46298/jnsao-2024-12235
Local properties and augmented Lagrangians in fully nonconvex composite optimizationArticle

Authors: Alberto De Marchi ; Patrick Mehlitz

    A broad class of optimization problems can be cast in composite form, that is, considering the minimization of the composition of a lower semicontinuous function with a differentiable mapping. This paper investigates the versatile template of composite optimization without any convexity assumptions. First- and second-order optimality conditions are discussed. We highlight the difficulties that stem from the lack of convexity when dealing with necessary conditions in a Lagrangian framework and when considering error bounds. Building upon these characterizations, a local convergence analysis is delineated for a recently developed augmented Lagrangian method, deriving rates of convergence in the fully nonconvex setting.


    Volume: Volume 5
    Section: Original research articles
    Published on: May 16, 2024
    Accepted on: May 14, 2024
    Submitted on: September 6, 2023
    Keywords: Mathematics - Optimization and Control,49J52, 49J53, 65K10, 90C30, 90C33

    Consultation statistics

    This page has been seen 199 times.
    This article's PDF has been downloaded 152 times.