Splitting methods with variable metric for Kurdyka-Łojasiewicz functions and general convergence rates
From MaRDI portal
Publication:2349844
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.
Recommendations
- Convergence of a Class of Nonmonotone Descent Methods for Kurdyka–Łojasiewicz Optimization Problems
- Proximal Alternating Minimization and Projection Methods for Nonconvex Problems: An Approach Based on the Kurdyka-Łojasiewicz Inequality
- The proximal alternating direction method of multipliers in the nonconvex setting: convergence analysis and rates
- Convergence of descent methods for semi-algebraic and tame problems: proximal algorithms, forward-backward splitting, and regularized Gauss-Seidel methods
- The Variable Metric Forward-Backward Splitting Algorithm Under Mild Differentiability Assumptions
Cites work
- A block coordinate descent method for regularized multiconvex optimization with applications to nonnegative tensor factorization and completion
- A block coordinate variable metric forward-backward algorithm
- A continuous dynamical Newton-like approach to solving monotone inclusions
- A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
- A proximal alternating linearization method for nonconvex optimization problems
- An iterative thresholding algorithm for linear inverse problems with a sparsity constraint
- Approximation of sparse controls in semilinear equations by piecewise linear functions
- Asymptotics for a class of non-linear evolution equations, with applications to geometric problems
- Characterizations of Łojasiewicz inequalities: Subgradient flows, talweg, convexity
- Clarke Subgradients of Stratifiable Functions
- Constructive solution of a bilinear optimal control problem for a Schrödinger equation
- Convergence and decay rate to equilibrium of bounded solutions of quasilinear parabolic equations
- Convergence in gradient-like systems which are asymptotically autonomous and analytic
- Convergence of descent methods for semi-algebraic and tame problems: proximal algorithms, forward-backward splitting, and regularized Gauss-Seidel methods
- Convergence of non-smooth descent methods using the Kurdyka-Łojasiewicz inequality
- Convergence of solutions to second-order gradient-like systems with analytic nonlinearities
- Convergence of the Iterates of Descent Methods for Analytic Cost Functions
- Convergence to equilibrium for the backward Euler scheme and applications
- Convergence to steady states in asymptotically autonomous semilinear evolution equations.
- Counting the faces of randomly-projected hypercubes and orthants, with applications
- Ergodic convergence to a zero of the sum of monotone operators in Hilbert space
- Finite termination of the proximal point algorithm
- For most large underdetermined systems of linear equations the minimal 𝓁1‐norm solution is also the sparsest solution
- Geometric categories and o-minimal structures
- Guaranteed minimum-rank solutions of linear matrix equations via nuclear norm minimization
- Hessian Riemannian Gradient Flows in Convex Programming
- scientific article; zbMATH DE number 1818892 (Why is no real title available?)
- scientific article; zbMATH DE number 563657 (Why is no real title available?)
- scientific article; zbMATH DE number 6142618 (Why is no real title available?)
- scientific article; zbMATH DE number 5586189 (Why is no real title available?)
- scientific article; zbMATH DE number 3341597 (Why is no real title available?)
- scientific article; zbMATH DE number 3371284 (Why is no real title available?)
- Interior proximal algorithm with variable metric for second-order cone programming: applications to structural optimization and support vector machines
- iPiano: inertial proximal algorithm for nonconvex optimization
- Local linear convergence for alternating and averaged nonconvex projections
- Monotone Operators and the Proximal Point Algorithm
- On gradients of functions definable in o-minimal structures
- On semi- and subanalytic geometry
- On the convergence of the proximal algorithm for nonsmooth functions involving analytic features
- Produits infinis de resolvantes
- Projected Newton Methods for Optimization Problems with Simple Constraints
- Proximal Alternating Minimization and Projection Methods for Nonconvex Problems: An Approach Based on the Kurdyka-Łojasiewicz Inequality
- Rank-Sparsity Incoherence for Matrix Decomposition
- Splitting Algorithms for the Sum of Two Nonlinear Operators
- The Łojasiewicz gradient inequality in the infinite-dimensional Hilbert space framework
- The Łojasiewicz Inequality for Nonsmooth Subanalytic Functions with Applications to Subgradient Dynamical Systems
- Two-Metric Projection Methods for Constrained Optimization
- Variable metric forward-backward algorithm for minimizing the sum of a differentiable function and a convex function
Cited in
(only showing first 100 items - show all)- Convergence rate analysis for the higher order power method in best rank one approximations of tensors
- Local convergence of the heavy-ball method and iPiano for non-convex optimization
- Approaching nonsmooth nonconvex optimization problems through first order dynamical systems with hidden acceleration and Hessian driven damping terms
- From error bounds to the complexity of first-order descent methods for convex functions
- On the proximal gradient algorithm with alternated inertia
- Calculus of the exponent of Kurdyka-Łojasiewicz inequality and its applications to linear convergence of first-order methods
- Proximal algorithms in statistics and machine learning
- A block coordinate variable metric linesearch based proximal gradient method
- Convergence rates of an inertial gradient descent algorithm under growth and flatness conditions
- Linear convergence of inexact descent method and inexact proximal gradient algorithms for lower-order regularization problems
- Local linear convergence of the alternating direction method of multipliers for nonconvex separable optimization problems
- Level-set subdifferential error bounds and linear convergence of Bregman proximal gradient method
- A block inertial Bregman proximal algorithm for nonsmooth nonconvex problems with application to symmetric nonnegative matrix tri-factorization
- An inexact proximal gradient algorithm with extrapolation for a class of nonconvex nonsmooth optimization problems
- A regularized alternating direction method of multipliers for a class of nonconvex problems
- Proximal gradient method for nonconvex and nonsmooth optimization on Hadamard manifolds
- Convergence and rate analysis of a proximal linearized ADMM for nonconvex nonsmooth optimization
- Convergence to equilibrium for time and space discretizations of the Cahn-Hilliard equation
- Perturbation techniques for convergence analysis of proximal gradient method and other first-order algorithms via variational analysis
- Restarting Frank-Wolfe: faster rates under Hölderian error bounds
- Block-coordinate and incremental aggregated proximal gradient methods for nonsmooth nonconvex problems
- A survey on some recent developments of alternating direction method of multipliers
- Global convergence of model function based Bregman proximal minimization algorithms
- A generalized proximal linearized algorithm for DC functions with application to the optimal size of the firm problem
- Kurdyka-Łojasiewicz exponent via inf-projection
- A gradient-type algorithm with backward inertial steps associated to a nonconvex minimization problem
- A proximal interior point algorithm with applications to image processing
- Variable metric techniques for forward-backward methods in imaging
- Multi-block nonconvex nonsmooth proximal ADMM: convergence and rates under Kurdyka-Łojasiewicz property
- Convergence rates for an inertial algorithm of gradient type associated to a smooth non-convex minimization
- Convergence of non-smooth descent methods using the Kurdyka-Łojasiewicz inequality
- A variational proximal alternating linearized minimization in a given metric for limited-angle CT image reconstruction
- Backward-forward algorithms for structured monotone inclusions in Hilbert spaces
- Serial and parallel approaches for image segmentation by numerical minimization of a second-order functional
- New convergence results for the inexact variable metric forward-backward method
- Convergence of the forward-backward algorithm: beyond the worst-case with the help of geometry
- An abstract convergence framework with application to inertial inexact forward-backward methods
- Variable metric inexact line-search-based methods for nonsmooth optimization
- An inertial forward-backward algorithm for the minimization of the sum of two nonconvex functions
- The Kurdyka-Łojasiewicz inequality as regularity condition
- Local minimizers of semi-algebraic functions from the viewpoint of tangencies
- An inertial Tseng's type proximal algorithm for nonsmooth and nonconvex optimization problems
- A forward-backward dynamical approach to the minimization of the sum of a nonsmooth convex with a smooth nonconvex function
- Forward-backward envelope for the sum of two nonconvex functions: further properties and nonmonotone linesearch algorithms
- Unifying abstract inexact convergence theorems and block coordinate variable metric iPiano
- A generalized inexact proximal point method for nonsmooth functions that satisfies Kurdyka Łojasiewicz inequality
- A remark on accelerated block coordinate descent for computing the proximity operators of a sum of convex functions
- Convergence of alternating direction method for minimizing sum of two nonconvex functions with linear constraints
- Sequence convergence of inexact nonconvex and nonsmooth algorithms with more realistic assumptions
- Variable Metric Forward-Backward Algorithm for Composite Minimization Problems
- On a general smoothly truncated regularization for variational piecewise constant image restoration: construction and convergent algorithms
- Proximal Gradient Methods for Machine Learning and Imaging
- Asynchronous variance-reduced block schemes for composite non-convex stochastic optimization: block-specific steplengths and adapted batch-sizes
- Thresholding gradient methods in Hilbert spaces: support identification and linear convergence
- The proximal alternating direction method of multipliers in the nonconvex setting: convergence analysis and rates
- General descent method using w-distance. Application to emergence of habits following worthwhile moves
- Convergence of inexact forward-backward algorithms using the forward-backward envelope
- Sharpness, restart, and acceleration
- Greedy approximate projection for magnetic resonance fingerprinting with partial volumes
- Convergence of iterative hard-thresholding algorithm with continuation
- Adaptive FISTA for Nonconvex Optimization
- Complexity of a quadratic penalty accelerated inexact proximal point method for solving linearly constrained nonconvex composite programs
- Proximal heterogeneous block implicit-explicit method and application to blind ptychographic diffraction imaging
- A comparison of edge-preserving approaches for differential interference contrast microscopy
- The Variable Metric Forward-Backward Splitting Algorithm Under Mild Differentiability Assumptions
- Learnable descent algorithm for nonsmooth nonconvex image reconstruction
- Extrapolated Proximal Subgradient Algorithms for Nonconvex and Nonsmooth Fractional Programs
- Hölderian Error Bounds and Kurdyka-Łojasiewicz Inequality for the Trust Region Subproblem
- On an iteratively reweighted linesearch based algorithm for nonconvex composite optimization
- An extrapolated iteratively reweighted \(\ell_1\) method with complexity analysis
- The convergence properties of infeasible inexact proximal alternating linearized minimization
- A class of modified accelerated proximal gradient methods for nonsmooth and nonconvex minimization problems
- Linear Convergence of a Proximal Alternating Minimization Method with Extrapolation for \(\boldsymbol{\ell_1}\) -Norm Principal Component Analysis
- An accelerated proximal algorithm for regularized nonconvex and nonsmooth bi-level optimization
- Convergence of Random Reshuffling under the Kurdyka–Łojasiewicz Inequality
- A forward-backward algorithm with different inertial terms for structured non-convex minimization problems
- The operator splitting schemes revisited: primal-dual gap and degeneracy reduction by a unified analysis
- Proximal gradient method with extrapolation and line search for a class of non-convex and non-smooth problems
- Template-based image reconstruction facing different topologies
- Convergence Analysis for Bregman Iterations in Minimizing a Class of Landau Free Energy Functionals
- Analysis of a variable metric block coordinate method under proximal errors
- A boosted-DCA with power-sum-DC decomposition for linearly constrained polynomial programs
- Convergence analysis of block majorize-minimize subspace approach
- A structured L-BFGS method and its application to inverse problems
- The level-set subdifferential error bound via Moreau envelopes
- Bregman methods for large-scale optimization with applications in imaging
- Extended angle conditions for the study of the asymptotic behaviour of some continuous and discrete forced dynamical systems
- Eigenvalue programming beyond matrices
- A VMiPG method for composite optimization with nonsmooth term having no closed-form proximal mapping
- Gradient descent provably escapes saddle points in the training of shallow ReLU networks
- Abstract generalized epsilon-descent algorithm
- Optimization models and approaches for strongly correlated electrons systems
- Variable metric proximal stochastic gradient methods with additional sampling
- Nonsmooth nonconvex-nonconcave minimax optimization: primal-dual balancing and iteration complexity analysis
- Stochastic optimization under hidden convexity
- A systematic approach to general higher-order majorization-minimization algorithms for (non)convex optimization
- Fast convergence to non-isolated minima: four equivalent conditions for \({\mathrm{C}^2}\) functions
- Convergence of descent optimization algorithms under Polyak-Łojasiewicz-Kurdyka conditions
- An inexact variable metric variant of incremental aggregated Forward-Backward method for the large-scale composite optimization problem
- Linesearch-enhanced forward-backward methods for inexact nonconvex scenarios
This page was built for publication: Splitting methods with variable metric for Kurdyka-Łojasiewicz functions and general convergence rates
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2349844)
