A telescopic Bregmanian proximal gradient method without the global Lipschitz continuity assumption
From MaRDI portal
Publication:2322358
Abstract: The problem of minimization of the sum of two convex functions has various theoretical and real-world applications. One of the popular methods for solving this problem is the proximal gradient method (proximal forward-backward algorithm). A very common assumption in the use of this method is that the gradient of the smooth term is globally Lipschitz continuous. However, this assumption is not always satisfied in practice, thus casting a limitation on the method. In this paper, we discuss, in a wide class of finite and infinite-dimensional spaces, a new variant of the proximal gradient method which does not impose the above-mentioned global Lipschitz continuity assumption. A key contribution of the method is the dependence of the iterative steps on a certain telescopic decomposition of the constraint set into subsets. Moreover, we use a Bregman divergence in the proximal forward-backward operation. Under certain practical conditions, a non-asymptotic rate of convergence (that is, in the function values) is established, as well as the weak convergence of the whole sequence to a minimizer. We also obtain a few auxiliary results of independent interest.
Recommendations
- A Bregman stochastic method for nonconvex nonsmooth problem beyond global Lipschitz gradient continuity
- A bundle Bregman proximal method for convex nondifferentiable minimization
- Proximal Minimization Methods with Generalized Bregman Functions
- Inertial proximal gradient methods with Bregman regularization for a class of nonconvex optimization problems
- Bregman Finito/MISO for nonconvex regularized finite sum minimization without Lipschitz gradient continuity
- scientific article; zbMATH DE number 7404502
- Approximate iterations in Bregman-function-based proximal algorithms
- Accelerated Bregman proximal gradient methods for relatively smooth convex optimization
- On the linear convergence of a Bregman proximal point algorithm
- A simple convergence analysis of Bregman proximal gradient algorithm
Cites work
- A descent lemma beyond Lipschitz gradient continuity: first-order methods revisited and applications
- A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
- A new convergence analysis and perturbation resilience of some accelerated proximal forward-backward algorithms with errors
- A relaxed version of Bregman's method for convex programming
- A telescopic Bregmanian proximal gradient method without the global Lipschitz continuity assumption
- An Iterative Regularization Method for Total Variation-Based Image Restoration
- An iterative row-action method for interval convex programming
- Approximation accuracy, gradient methods, and error bound for structured convex optimization
- Auxiliary problem principle and decomposition of optimization problems
- Bregman Iterative Algorithms for \ell₁-Minimization with Applications to Compressed Sensing
- Convergence Analysis of a Proximal-Like Minimization Algorithm Using Bregman Functions
- Convergence of a proximal point method in the presence of computational errors in Hilbert spaces
- Convex Analysis
- Convex analysis and monotone operator theory in Hilbert spaces
- Convex functions, monotone operators and differentiability.
- Elastic-net regularization in learning theory
- Ergodic convergence to a zero of the sum of monotone operators in Hilbert space
- ESSENTIAL SMOOTHNESS, ESSENTIAL STRICT CONVEXITY, AND LEGENDRE FUNCTIONS IN BANACH SPACES
- First order methods beyond convexity and Lipschitz gradient continuity with applications to quadratic inverse problems
- Forward-backward splitting with Bregman distances
- Functional analysis, Sobolev spaces and partial differential equations
- scientific article; zbMATH DE number 1807400 (Why is no real title available?)
- scientific article; zbMATH DE number 3901504 (Why is no real title available?)
- scientific article; zbMATH DE number 3971584 (Why is no real title available?)
- scientific article; zbMATH DE number 51872 (Why is no real title available?)
- scientific article; zbMATH DE number 3595777 (Why is no real title available?)
- scientific article; zbMATH DE number 1968250 (Why is no real title available?)
- scientific article; zbMATH DE number 3296905 (Why is no real title available?)
- scientific article; zbMATH DE number 3341597 (Why is no real title available?)
- Image deblurring with Poisson data: from cells to galaxies
- Introductory lectures on convex optimization. A basic course.
- Iterations of paracontractions and firmaly nonexpansive operators with applications to feasibility and optimization
- Mirror descent and nonlinear projected subgradient methods for convex optimization.
- Monotone Operators and the Proximal Point Algorithm
- On the convergence of the forward-backward splitting method with linesearches
- Optimization with sparsity-inducing penalties
- Produits infinis de resolvantes
- Prox-Method with Rate of Convergence O(1/t) for Variational Inequalities with Lipschitz Continuous Monotone Operators and Smooth Convex-Concave Saddle Point Problems
- Proximal minimization algorithm with \(D\)-functions
- Re-examination of Bregman functions and new properties of their divergences
- Signal Recovery by Proximal Forward-Backward Splitting
- Solutions to inexact resolvent inclusion problems with applications to nonlinear analysis and optimization
- Stability of the optimal values under small perturbations of the constraint set
- Strong convergence of contraction semigroups and of iterative methods for accretive operators in Banach spaces
- The Bregman distance without the Bregman function. II
Cited in
(12)- Convergence properties of monotone and nonmonotone proximal gradient methods revisited
- Fast and simple Bregman projection methods for solving variational inequalities and related problems in Banach spaces
- Bregman proximal mappings and Bregman-Moreau envelopes under relative prox-regularity
- A telescopic Bregmanian proximal gradient method without the global Lipschitz continuity assumption
- Re-examination of Bregman functions and new properties of their divergences
- A descent lemma beyond Lipschitz gradient continuity: first-order methods revisited and applications
- Convergence Analysis of the Proximal Gradient Method in the Presence of the Kurdyka–Łojasiewicz Property Without Global Lipschitz Assumptions
- A Bregman stochastic method for nonconvex nonsmooth problem beyond global Lipschitz gradient continuity
- Convergence analysis of a new Bregman extragradient method for solving fixed point problems and variational inequality problems in reflexive Banach spaces
- Convergence Analysis for Bregman Iterations in Minimizing a Class of Landau Free Energy Functionals
- Strong convergence theorem of a new modified Bregman extragradient method to solve fixed point problems and variational inequality problems in general reflexive Banach spaces
- A C-FISTA-type proximal point algorithm for strongly quasiconvex pseudomonotone equilibrium problems
This page was built for publication: A telescopic Bregmanian proximal gradient method without the global Lipschitz continuity assumption
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2322358)
