Splitting methods with variable metric for KL functions

Abstract

We study the convergence of general abstract descent methods applied to a lower semicontinuous nonconvex function f that satisfies the Kurdyka-Lojasiewicz inequality in a Hilbert space. We prove that any precompact sequence converges to a critical point of f and obtain new convergence rates both for the values and the iterates. The analysis covers alternating versions of the forward-backward method with variable metric and relative errors. As an example, a nonsmooth and nonconvex version of the Levenberg-Marquardt algorithm is detailled.

References in corpus (1)

• Hessian Riemannian gradient flows in convex programming

Cited by in corpus (42)

• Calculus of the exponent of Kurdyka-Łojasiewicz inequality and its applications to linear convergence of first-order methods
• Forward-backward envelope for the sum of two nonconvex functions: Further properties and nonmonotone line-search algorithms
• Variable metric inexact line-search based methods for nonsmooth optimization
• On the convergence of a linesearch based proximal-gradient method for nonconvex optimization
• New convergence results for the scaled gradient projection method
• Interdependent Strategic Security Risk Management with Bounded Rationality in the Internet of Things
• Extrapolated Proximal Subgradient Algorithms for Nonconvex and Nonsmooth Fractional Programs
• Non-convex optimization for self-calibration of direction-dependent effects in radio interferometric imaging
• Time-Varying Convex Optimization via Time-Varying Averaged Operators
• Hybrid ISTA: Unfolding ISTA With Convergence Guarantees Using Free-Form Deep Neural Networks
• The Asynchronous PALM Algorithm for Nonsmooth Nonconvex Problems
• A structured L-BFGS method and its application to inverse problems
• Block-coordinate and incremental aggregated proximal gradient methods for nonsmooth nonconvex problems
• Proximal Gradient Algorithms: Applications in Signal Processing
• Convergence of the Forward-Backward Algorithm: Beyond the Worst Case with the Help of Geometry
• Proximal Gradient Method with Extrapolation and Line Search for a Class of Nonconvex and Nonsmooth Problems
• Greedy Approximate Projection for Magnetic Resonance Fingerprinting with Partial Volumes
• Proximal Gradient Descent-Ascent: Variable Convergence under KŁ Geometry
• Complexity of a quadratic penalty accelerated inexact proximal point method for solving linearly constrained nonconvex composite programs
• Perturbation techniques for convergence analysis of proximal gradient method and other first-order algorithms via variational analysis
• Convergence Analysis of a Momentum Algorithm with Adaptive Step Size for Non Convex Optimization
• An abstract convergence framework with application to inertial inexact forward--backward methods
• Learnable Descent Algorithm for Nonsmooth Nonconvex Image Reconstruction
• Thresholding gradient methods in Hilbert spaces: support identification and linear convergence
• The Convergence Properties of Infeasible Inexact Proximal Alternating Linearized Minimization
• A convergence framework for inexact nonconvex and nonsmooth algorithms and its applications to several iterations
• Accelerated Inexact First-Order Methods for Solving Nonconvex Composite Optimization Problems
• A regularized tri-linear approach for optical interferometric imaging
• Gradient descent provably escapes saddle points in the training of shallow ReLU networks
• Unifying abstract inexact convergence theorems and block coordinate variable metric iPiano
• A Variational Approach on Level sets and Linear Convergence of Variable Bregman Proximal Gradient Method for Nonconvex Optimization Problems
• Eigenvalue programming beyond matrices
• A Preconditioned Version of a Nested Primal-Dual Algorithm for Image Deblurring
• A trust region-type normal map-based semismooth Newton method for nonsmooth nonconvex composite optimization
• An Optimization Framework with Flexible Inexact Inner Iterations for Nonconvex and Nonsmooth Programming
• Convergence rates and approximation results for SGD and its continuous-time counterpart
• DCA based Algorithm with Extrapolation for Nonconvex Nonsmooth Optimization
• Proximal Dogleg Opportunistic Majorization for Nonconvex and Nonsmooth Optimization
• Linear convergence of inexact descent method and inexact proximal gradient algorithms for lower-order regularization problems
• Level-set Subdifferential Error Bounds and Linear Convergence of Variable Bregman Proximal Gradient Method
• An inertial forward-backward algorithm for the minimization of the sum of two nonconvex functions
• Asynchronous Variance-reduced Block Schemes for Composite Nonconvex Stochastic Optimization: Block-specific Steplengths and Adapted Batch-sizes