The Variable Metric Forward-Backward Splitting Algorithm Under Mild Differentiability Assumptions
From MaRDI portal
Publication:5363380
DOI10.1137/16M1073741zbMATH Open1375.65085arXiv1605.00952MaRDI QIDQ5363380FDOQ5363380
Authors: Saverio Salzo 
Publication date: 6 October 2017
Published in: SIAM Journal on Optimization (Search for Journal in Brave)
Abstract: We study the variable metric forward-backward splitting algorithm for convex minimization problems without the standard assumption of the Lipschitz continuity of the gradient. In this setting, we prove that, by requiring only mild assumptions on the smooth part of the objective function and using several types of line search procedures for determining either the gradient descent stepsizes, or the relaxation parameters, one still obtains weak convergence of the iterates and convergence in the objective function values. Moreover, the convergence rate in the function values is obtained if slightly stronger differentiability assumptions are added. We also illustrate several applications including problems that involve Banach spaces and functions of divergence type.
Full work available at URL: https://arxiv.org/abs/1605.00952
Recommendations
- Convergence analysis of a variable metric forward-backward splitting algorithm with applications
- Variable metric forward-backward splitting with applications to monotone inclusions in duality
- scientific article; zbMATH DE number 1749789
- The forward-backward splitting methods for variational inequalities and minimization problems in Banach spaces
- New convergence results for the inexact variable metric forward-backward method
- Forward-backward resolvent splitting methods for general mixed variational inequalities
- A Variable Metric Extension of the Forward–Backward–Forward Algorithm for Monotone Operators
- Relaxed forward-backward splitting methods for solving variational inclusions and applications
- Variable Metric Forward-Backward Algorithm for Composite Minimization Problems
- A self-adaptive forward-backward-forward algorithm for solving split variational inequalities
forward-backward algorithmconvex optimizationnumerical examplesglobal convergenceconvergence ratesvariable metricinexact line search methodsquasi-Fejér sequences
Cites Work
- A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
- Title not available (Why is that?)
- Convex analysis and monotone operator theory in Hilbert spaces
- Title not available (Why is that?)
- A coordinate gradient descent method for nonsmooth separable minimization
- Signal Recovery by Proximal Forward-Backward Splitting
- Projected gradient methods for linearly constrained problems
- Regularization methods in Banach spaces.
- An iterative thresholding algorithm for linear inverse problems with a sparsity constraint
- What is the Subdifferential of the Closed Convex Hull of a Function?
- Convex programming in Hilbert space
- Convergence of descent methods for semi-algebraic and tame problems: proximal algorithms, forward-backward splitting, and regularized Gauss-Seidel methods
- Title not available (Why is that?)
- Title not available (Why is that?)
- A Modified Forward-Backward Splitting Method for Maximal Monotone Mappings
- Quasi-Fejérian analysis of some optimization algorithms
- Two-Metric Projection Methods for Constrained Optimization
- Convergence Rates in Forward--Backward Splitting
- Variable metric forward-backward splitting with applications to monotone inclusions in duality
- Title not available (Why is that?)
- Variable metric quasi-Fejér monotonicity
- Splitting methods with variable metric for Kurdyka-Łojasiewicz functions and general convergence rates
- Variable metric forward-backward algorithm for minimizing the sum of a differentiable function and a convex function
- On the Goldstein-Levitin-Polyak gradient projection method
- Convergence rate analysis of several splitting schemes
- Full convergence of the steepest descent method with inexact line searches
- The Gradient Projection Method under Mild Differentiability Conditions
- The Baillon-Haddad theorem revisited
- A forward–backward splitting algorithm for the minimization of non-smooth convex functionals in Banach space
- A Class of Inexact Variable Metric Proximal Point Algorithms
- Composite self-concordant minimization
- On the convergence of primal-dual hybrid gradient algorithms for total variation image restoration
- Compositions and convex combinations of averaged nonexpansive operators
- Proximal Newton-type methods for minimizing composite functions
- On the convergence properties of the projected gradient method for convex optimization
- Title not available (Why is that?)
- Alternating proximal regularized dictionary learning
- Variable metric inexact line-search-based methods for nonsmooth optimization
- Modified Fejér sequences and applications
- New convergence results for the scaled gradient projection method
- On the convergence of the forward-backward splitting method with linesearches
Cited In (43)
- Forward-backward algorithm for functions with locally Lipschitz gradient: applications to mean field games
- Global complexity analysis of inexact successive quadratic approximation methods for regularized optimization under mild assumptions
- A novel stepsize for gradient descent method
- An accelerated forward-backward-half forward splitting algorithm for monotone inclusion with applications to image restoration
- On the convergence of the forward-backward splitting method with linesearches
- An interior proximal gradient method for nonconvex optimization
- Proximal Gradient Methods for Machine Learning and Imaging
- An inexact successive quadratic approximation method for a class of difference-of-convex optimization problems
- A Regularized Newton Method for \({\boldsymbol{\ell}}_{q}\) -Norm Composite Optimization Problems
- Variable metric forward-backward algorithm for minimizing the sum of a differentiable function and a convex function
- A Variable Metric Extension of the Forward–Backward–Forward Algorithm for Monotone Operators
- Variable metric techniques for forward-backward methods in imaging
- Parallel random block-coordinate forward-backward algorithm: a unified convergence analysis
- Splitting methods with variable metric for Kurdyka-Łojasiewicz functions and general convergence rates
- Variable Metric Forward-Backward Algorithm for Composite Minimization Problems
- The forward-backward splitting method for finding the minimum like-norm solution of the mixed variational inequality problem
- A proximal interior point algorithm with applications to image processing
- Convergence of the forward-backward algorithm: beyond the worst-case with the help of geometry
- Proximal gradient algorithms under local Lipschitz gradient continuity. A convergence and robustness analysis of PANOC
- Convergence Analysis for Bregman Iterations in Minimizing a Class of Landau Free Energy Functionals
- A block coordinate variable metric linesearch based proximal gradient method
- A VMiPG method for composite optimization with nonsmooth term having no closed-form proximal mapping
- On the linear convergence of forward-backward splitting method. I: Convergence analysis
- Quadratic growth conditions and uniqueness of optimal solution to Lasso
- Novel algorithms based on forward-backward splitting technique: effective methods for regression and classification
- Modified Fejér sequences and applications
- On the finite termination of the gradient projection method
- Generalized support vector regression: duality and tensor-kernel representation
- An inexact gradient mirror descent algorithm for non-smooth convex optimization
- Forward-Backward-Half Forward Algorithm for Solving Monotone Inclusions
- The forward-backward splitting method for non-Lipschitz continuous minimization problems in Banach spaces
- Proximal extrapolated gradient methods for variational inequalities
- Metric selection in fast dual forward-backward splitting
- Parallel Normal S-Iteration Methods with Applications to Optimization Problems
- Four-operator splitting via a forward-backward-half-forward algorithm with line search
- Convergence analysis of a variable metric forward-backward splitting algorithm with applications
- Forward-backward penalty scheme for constrained convex minimization without inf-compactness
- New convergence results for the inexact variable metric forward-backward method
- A new proximal heavy ball inexact line-search algorithm
- Convergence of the exponentiated gradient method with Armijo line search
- The developments of proximal point algorithms
- Bregman forward-backward operator splitting
- Multi-step inertial forward-backward-half forward algorithm for solving monotone inclusion
This page was built for publication: The Variable Metric Forward-Backward Splitting Algorithm Under Mild Differentiability Assumptions
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5363380)
