An Accelerated Inexact Dampened Augmented Lagrangian Method for Linearly-Constrained Nonconvex Composite Optimization Problems
Preprint
Abstract
This paper proposes and analyzes an accelerated inexact dampened augmented Lagrangian (AIDAL) method for solving linearly-constrained nonconvex composite optimization problems. Each iteration of the AIDAL method consists of: (i) inexactly solving a dampened proximal augmented Lagrangian (AL) subproblem by calling an accelerated composite gradient (ACG) subroutine; (ii) applying a dampened and under-relaxed Lagrange multiplier update; and (iii) using a novel test to check whether the penalty parameter of the AL function should be increased. Under several mild assumptions involving the dampening factor and the under-relaxation constant, it is shown that the AIDAL method generates an approximate stationary point of the constrained problem in ${\cal O}(\varepsilon^{-5/2}\log\varepsilon^{-1})$ iterations of the ACG subroutine, for a given tolerance $\varepsilon>0$. Numerical experiments are also given to show the computational efficiency of the proposed method.
Keywords
All Related Versions
This publication has 22 references indexed in Scilit:
- Stochastic first-order methods for convex and nonconvex functional constrained optimizationMathematical Programming, 2022
- An efficient adaptive accelerated inexact proximal point method for solving linearly constrained nonconvex composite problemsComputational Optimization and Applications, 2020
- Iteration complexity of inexact augmented Lagrangian methods for constrained convex programmingMathematical Programming, 2019
- Perturbed proximal primal–dual algorithm for nonconvex nonsmooth optimizationMathematical Programming, 2019
- Structured nonconvex and nonsmooth optimization: algorithms and iteration complexity analysisComputational Optimization and Applications, 2018
- Complexity of first-order inexact Lagrangian and penalty methods for conic convex programmingOptimization Methods and Software, 2017
- Adaptive inexact fast augmented Lagrangian methods for constrained convex optimizationOptimization Letters, 2016
- An adaptive accelerated first-order method for convex optimizationComputational Optimization and Applications, 2015
- Iteration-complexity of first-order augmented Lagrangian methods for convex programmingMathematical Programming, 2015
- Iteration-complexity of first-order penalty methods for convex programmingMathematical Programming, 2012