Proximal gradient method with extrapolation and line search for a class of non-convex and non-smooth problems

DOI10.1007/S10957-023-02348-4arXiv1711.06831OpenAlexW4389942280MaRDI QIDQ6182324FDOQ6182324

Authors:

Publication date: 25 January 2024

Published in: Journal of Optimization Theory and Applications (Search for Journal in Brave)

Abstract: In this paper, we consider a class of possibly nonconvex, nonsmooth and non-Lipschitz optimization problems arising in many contemporary applications such as machine learning, variable selection and image processing. To solve this class of problems, we propose a proximal gradient method with extrapolation and line search (PGels). This method is developed based on a special potential function and successfully incorporates both extrapolation and non-monotone line search, which are two simple and efficient accelerating techniques for the proximal gradient method. Thanks to the line search, this method allows more flexibilities in choosing the extrapolation parameters and updates them adaptively at each iteration if a certain line search criterion is not satisfied. Moreover, with proper choices of parameters, our PGels reduces to many existing algorithms. We also show that, under some mild conditions, our line search criterion is well defined and any cluster point of the sequence generated by PGels is a stationary point of our problem. In addition, by assuming the Kurdyka-$L$ojasiewicz exponent of the objective in our problem, we further analyze the local convergence rate of two special cases of PGels, including the widely used non-monotone proximal gradient method as one case. Finally, we conduct some numerical experiments for solving the $el{l}_1$ regularized logistic regression problem and the $el{l}_{1ext-2}$ regularized least squares problem. Our numerical results illustrate the efficiency of PGels and show the potential advantage of combining two accelerating techniques.

Full work available at URL: https://arxiv.org/abs/1711.06831

Recommendations

• An inexact proximal gradient algorithm with extrapolation for a class of nonconvex nonsmooth optimization problems
• Linear convergence of proximal gradient algorithm with extrapolation for a class of nonconvex nonsmooth minimization problems
• A class of modified accelerated proximal gradient methods for nonsmooth and nonconvex minimization problems
• Some accelerated alternating proximal gradient algorithms for a class of nonconvex nonsmooth problems
• scientific article; zbMATH DE number 7404502

zbMATH Keywords

proximal gradient methodextrapolationline searchstationary pointnon-monotoneKL property

Mathematics Subject Classification ID

Numerical mathematical programming methods (65K05) Applications of mathematical programming (90C90) Nonconvex programming, global optimization (90C26) Nonlinear programming (90C30)

Cites Work

• A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
• Templates for convex cone problems with applications to sparse signal recovery
• iPiano: inertial proximal algorithm for nonconvex optimization
• Nearly unbiased variable selection under minimax concave penalty
• Variable Selection via Nonconcave Penalized Likelihood and its Oracle Properties
• Title not available (Why is that?)
• Splitting Algorithms for the Sum of Two Nonlinear Operators
• Variational Analysis
• Introductory lectures on convex optimization. A basic course.
• Asymptotics for Lasso-type estimators.
• Adaptive restart for accelerated gradient schemes
• Title not available (Why is that?)
• Gradient methods for minimizing composite functions
• Nonmonotone Spectral Projected Gradient Methods on Convex Sets
• A Nonmonotone Line Search Technique and Its Application to Unconstrained Optimization
• Asymptotic properties of bridge estimators in sparse high-dimensional regression models
• Fast Gradient-Based Algorithms for Constrained Total Variation Image Denoising and Deblurring Problems
• Smoothing methods for nonsmooth, nonconvex minimization
• Proximal splitting methods in signal processing
• Proximal Alternating Minimization and Projection Methods for Nonconvex Problems: An Approach Based on the Kurdyka-Łojasiewicz Inequality
• Proximal alternating linearized minimization for nonconvex and nonsmooth problems
• Sparse Reconstruction by Separable Approximation
• A block coordinate descent method for regularized multiconvex optimization with applications to nonnegative tensor factorization and completion
• A generalized proximal point algorithm for certain non-convex minimization problems
• A Nonmonotone Line Search Technique for Newton’s Method
• Efficient Reconstruction of Piecewise Constant Images Using Nonsmooth Nonconvex Minimization
• Approximation accuracy, gradient methods, and error bound for structured convex optimization
• Convergence of descent methods for semi-algebraic and tame problems: proximal algorithms, forward-backward splitting, and regularized Gauss-Seidel methods
• Accelerated gradient methods for nonconvex nonlinear and stochastic programming
• A proximal method for composite minimization
• The Łojasiewicz Inequality for Nonsmooth Subanalytic Functions with Applications to Subgradient Dynamical Systems
• Splitting methods with variable metric for Kurdyka-Łojasiewicz functions and general convergence rates
• On the convergence of the proximal algorithm for nonsmooth functions involving analytic features
• Minimization of \(\ell_{1-2}\) for compressed sensing
• On the nonmonotone line search
• Sparse Recovery via Partial Regularization: Models, Theory, and Algorithms
• An introduction to continuous optimization for imaging
• Penalty methods for a class of non-Lipschitz optimization problems
• A globally convergent algorithm for nonconvex optimization based on block coordinate update
• Group sparse optimization via \(\ell_{p,q}\) regularization
• A nonmonotone alternating updating method for a class of matrix factorization problems
• Calculus of the exponent of Kurdyka-Łojasiewicz inequality and its applications to linear convergence of first-order methods
• Linear convergence of proximal gradient algorithm with extrapolation for a class of nonconvex nonsmooth minimization problems
• Difference-of-convex learning: directional stationarity, optimality, and sparsity
• A proximal difference-of-convex algorithm with extrapolation
• Further properties of the forward-backward envelope with applications to difference-of-convex programming
• Block stochastic gradient iteration for convex and nonconvex optimization
• A successive difference-of-convex approximation method for a class of nonconvex nonsmooth optimization problems

Cited In (2)

• A class of modified accelerated proximal gradient methods for nonsmooth and nonconvex minimization problems
• Fast gradient algorithm with dry-like friction and nonmonotone line search for nonconvex optimization problems

This page was built for publication: Proximal gradient method with extrapolation and line search for a class of non-convex and non-smooth problems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6182324)