Local properties and augmented Lagrangians in fully nonconvex composite optimization
arXiv:2309.01980 · doi:10.46298/jnsao-2024-12235
Abstract
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.
36 pages
References in corpus (6)
- Optimality conditions for disjunctive programs based on generalized differentiation with application to mathematical programs with equilibrium constraints
- Constrained composite optimization and augmented Lagrangian methods
- Proximal Gradient Algorithms under Local Lipschitz Gradient Continuity: A Convergence and Robustness Analysis of PANOC
- Implicit augmented Lagrangian and generalized optimization
- Why second-order sufficient conditions are, in a way, easy -- or -- revisiting calculus for second subderivatives
- Convergence of Augmented Lagrangian Methods for Composite Optimization Problems