English

Convergence of Augmented Lagrangian Methods for Composite Optimization Problems

Optimization and Control 2023-10-23 v2

Abstract

Local convergence analysis of the augmented Lagrangian method (ALM) is established for a large class of composite optimization problems with nonunique Lagrange multipliers under a second-order sufficient condition. We present a new second-order variational property, called the semi-stability of second subderivatives, and demonstrate that it is widely satisfied for numerous classes of functions, important for applications in constrained and composite optimization problems. Using the latter condition and a certain second-order sufficient condition, we are able to establish Q-linear convergence of the primal-dual sequence for an inexact version of the ALM for composite programs.

Keywords

Cite

@article{arxiv.2307.15627,
  title  = {Convergence of Augmented Lagrangian Methods for Composite Optimization Problems},
  author = {Nguyen T. V. Hang and Ebrahim Sarabi},
  journal= {arXiv preprint arXiv:2307.15627},
  year   = {2023}
}
R2 v1 2026-06-28T11:42:58.680Z