Convergence Analysis of the Proximal Gradient Method in the Presence of the Kurdyka-Łojasiewicz Property without Global Lipschitz Assumptions

2023/01/12 by Xiaoxi Jia, Jia, Xiaoxi, Christian Kanzow +3 · 6 citations
Computer Science · Engineering · Mathematics · #Optimization and Variational Analysis #Sparse and Compressive Sensing Techniques #Advanced Optimization Algorithms Research

paper · pdf · doi:10.48550/arxiv.2301.05002

Abstract

We consider a composite optimization problem where the sum of a continuously differentiable and a merely lower semicontinuous function has to be minimized. The proximal gradient algorithm is the classical method for solving such a problem numerically. The corresponding global convergence and local rate-of-convergence theory typically assumes, besides some technical conditions, that the smooth function has a globally Lipschitz continuous gradient and that the objective function satisfies the Kurdyka-Łojasiewicz property. Though this global Lipschitz assumption is satisfied in several applications where the objective function is, e.g., quadratic, this requirement is very restrictive in the non-quadratic case. Some recent contributions therefore try to overcome this global Lipschitz condition by replacing it with a local one, but, to the best of our knowledge, they still require some extra condition in order to obtain the desired global and rate-of-convergence results. The aim of this paper is to show that the local Lipschitz assumption together with the Kurdyka-Łojasiewicz property is sufficient to recover these convergence results.

Cited by

• Linear convergence of relocated fixed-point iterations
• A nonmonotone extrapolated proximal gradient-subgradient algorithm beyond global Lipschitz gradient continuity
• Proximal gradient methods in Banach spaces
• Simple linesearch-free first-order methods for nonconvex optimization
• General Proximal Quasi-Newton Methods based on model functions for nonsmooth nonconvex problems
• On Information Geometry and Iterative Optimization in Model Compression: Operator Factorization

Related

• Convergence of Nonmonotone Proximal Gradient Methods under the Kurdyka-Lojasiewicz Property without a Global Lipschitz Assumption
• Convergence analysis of nonmonotone proximal gradient methods under local Lipschitz continuity and Kurdyka--Łojasiewicz property
• Convergence Properties of Monotone and Nonmonotone Proximal Gradient Methods Revisited
• Linear Convergence of the Proximal Gradient Method for Composite Optimization Under the Polyak-Łojasiewicz Inequality and Its Variant
• A nonmonotone extrapolated proximal gradient-subgradient algorithm beyond global Lipschitz gradient continuity