An Inexact Augmented Lagrangian Framework for Nonconvex Optimization with Nonlinear Constraints
Abstract
We propose a practical inexact augmented Lagrangian method (iALM) for nonconvex problems with nonlinear constraints. We characterize the total computational complexity of our method subject to a verifiable geometric condition, which is closely related to the Polyak-Lojasiewicz and Mangasarian-Fromowitz conditions. In particular, when a first-order solver is used for the inner iterates, we prove that iALM finds a first-order stationary point with calls to the first-order oracle. If, in addition, the problem is smooth and a second-order solver is used for the inner iterates, iALM finds a second-order stationary point with calls to the second-order oracle, which matches the known theoretical complexity result in the literature. We also provide strong numerical evidence on large-scale machine learning problems, including the Burer-Monteiro factorization of semidefinite programs, and a novel nonconvex relaxation of the standard basis pursuit template. For these examples, we also show how to verify our geometric condition.
Cite
@article{arxiv.1906.11357,
title = {An Inexact Augmented Lagrangian Framework for Nonconvex Optimization with Nonlinear Constraints},
author = {Mehmet Fatih Sahin and Armin Eftekhari and Ahmet Alacaoglu and Fabian Latorre and Volkan Cevher},
journal= {arXiv preprint arXiv:1906.11357},
year = {2022}
}