Rate-improved Inexact Augmented Lagrangian Method for Constrained Nonconvex Optimization

MaRDI QIDQ6344311zbMATH OpenFDO

Authors Zichong Li, Pin-Yu Chen, Sijia Liu, Songtao Lu, Yangyang Xu

Publication date 2 July 2020

Mathematics Subject Classification ID

Convex programming (90C25) Nonconvex programming, global optimization (90C26) Nonlinear programming (90C30) Abstract computational complexity for mathematical programming problems (90C60)

Abstract: First-order methods have been studied for nonlinear constrained optimization within the framework of the augmented Lagrangian method (ALM) or penalty method. We propose an improved inexact ALM (iALM) and conduct a unified analysis for nonconvex problems with either affine equality or nonconvex constraints. Under certain regularity conditions (that are also assumed by existing works), we show an $ildeO(varepsilo{n}^{-frac52})$ complexity result for a problem with a nonconvex objective and affine equality constraints and an $ildeO(varepsilo{n}^{-3})$ complexity result for a problem with a nonconvex objective and nonconvex constraints, where the complexity is measured by the number of first-order oracles to yield an $varepsilon$-KKT solution. Both results are the best known. The same-order complexity results have been achieved by penalty methods. However, two different analysis techniques are used to obtain the results, and more importantly, the penalty methods generally perform significantly worse than iALM in practice. Our improved iALM and analysis close the gap between theory and practice. Numerical experiments on nonconvex problems with affine equality or nonconvex constraints are provided to demonstrate the effectiveness of our proposed method.

This page was built for publication: Rate-improved Inexact Augmented Lagrangian Method for Constrained Nonconvex Optimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6344311)