Gradient methods with regularization for constrained optimization problems and their complexity estimates
From MaRDI portal
Abstract: We suggest simple implementable modifications of conditional gradient and gradient projection methods for smooth convex optimization problems in Hilbert spaces. Usually, the custom methods attain only weak convergence. We prove strong convergence of the new versions and establish their complexity estimates, which appear similar to the convergence rate of the weakly convergent versions.
Recommendations
- Optimality and complexity for constrained optimization problems with nonconvex regularization
- Regularized gradient-projection methods for equilibrium and constrained convex minimization problems
- Regularized projection and conditional gradient methods in convex finite-dimensional optimization problems
- Constrained gradient method for nonsmooth optimization problems
- On regularization and active-set methods with complexity for constrained optimization
- Regularized gradient-projection methods for finding the minimum-norm solution of the constrained convex minimization problem
- On constrained optimization with nonconvex regularization
- Gradient methods for constrained maxima
- Regularized optimization methods for convex MINLP problems
- A general regularized gradient-projection method for solving equilibrium and constrained convex minimization problems
Cites work
- Convergence Rates for Conditional Gradient Sequences Generated by Implicit Step Length Rules
- scientific article; zbMATH DE number 3881348 (Why is no real title available?)
- scientific article; zbMATH DE number 41702 (Why is no real title available?)
- scientific article; zbMATH DE number 3486541 (Why is no real title available?)
- scientific article; zbMATH DE number 3597791 (Why is no real title available?)
- scientific article; zbMATH DE number 1925644 (Why is no real title available?)
- scientific article; zbMATH DE number 936298 (Why is no real title available?)
- scientific article; zbMATH DE number 3227378 (Why is no real title available?)
- The Method of Pairwise Variations with Tolerances for Linearly Constrained Optimization Problems
Cited in
(14)- Incrementally updated gradient methods for constrained and regularized optimization
- Adaptive conditional gradient method
- AN EXPONENTIAL LOWER BOUND ON THE COMPLEXITY OF REGULARIZATION PATHS
- The Constrained Least Gradient Problem in R n
- Regularized projection and conditional gradient methods in convex finite-dimensional optimization problems
- scientific article; zbMATH DE number 3516928 (Why is no real title available?)
- scientific article; zbMATH DE number 3637739 (Why is no real title available?)
- Worst-case evaluation complexity of regularization methods for smooth unconstrained optimization using Hölder continuous gradients
- Simplified versions of the conditional gradient method
- scientific article; zbMATH DE number 834483 (Why is no real title available?)
- An efficient gradient method with approximately optimal stepsizes based on regularization models for unconstrained optimization
- Gradient iteration with \(\ell _{p}\)-norm constraints
- Approximation accuracy, gradient methods, and error bound for structured convex optimization
- Gradient-Type Methods for Optimization Problems with Polyak-Łojasiewicz Condition: Early Stopping and Adaptivity to Inexactness Parameter
This page was built for publication: Gradient methods with regularization for constrained optimization problems and their complexity estimates
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4643688)
