Simplified versions of the conditional gradient method
From MaRDI portal
Abstract: We suggest simple modifications of the conditional gradient method for smooth optimization problems, which maintain the basic convergence properties, but reduce the implementation cost of each iteration essentially. Namely, we propose the step-size procedure without any line-search, and inexact solution of the direction finding subproblem. Preliminary results of computational tests confirm efficiency of the proposed modifications.
Recommendations
- Conditional gradient method without line-search
- Gradient methods with regularization for constrained optimization problems and their complexity estimates
- Adaptive conditional gradient method
- A variant of the constrained gradient method
- Modification of gradient type methods in optimal control problems
Cites work
- A conditional gradient method with linear rate of convergence for solving convex linear systems
- An adaptive partial linearization method for optimization problems on product sets
- Conditional gradient algorithms with open loop step size rules
- Conditional gradient method without line-search
- Convergence Rates for Conditional Gradient Sequences Generated by Implicit Step Length Rules
- Coresets, sparse greedy approximation, and the Frank-Wolfe algorithm
- scientific article; zbMATH DE number 3597791 (Why is no real title available?)
- New analysis and results for the Frank-Wolfe method
- Selective bi-coordinate variations for resource allocation type problems
- Some comments on Wolfe's ‘away step’
- The Method of Pairwise Variations with Tolerances for Linearly Constrained Optimization Problems
Cited in
(17)- Conditional gradient method without line-search
- Conditional gradient method for multiobjective optimization
- Variational inequality type formulations of general market equilibrium problems with local information
- Hybrid methods for network equilibrium problems
- Frank-Wolfe and friends: a journey into projection-free first-order optimization methods
- Adaptive conditional gradient method
- A non-monotone conjugate subgradient type method for minimization of convex functions
- Improved complexities for stochastic conditional gradient methods under interpolation-like conditions
- Concise representation of generalised gradients
- scientific article; zbMATH DE number 4057300 (Why is no real title available?)
- Conditional gradient algorithms for norm-regularized smooth convex optimization
- On the Frank-Wolfe algorithm for non-compact constrained optimization problems
- Subgradient method with feasible inexact projections for constrained convex optimization problems
- Inexact partial linearization methods for network equilibrium problems
- scientific article; zbMATH DE number 7064051 (Why is no real title available?)
- Self-adaptive algorithms for quasiconvex programming and applications to machine learning
- Adaptive generalized conditional gradient method for multiobjective optimization
This page was built for publication: Simplified versions of the conditional gradient method
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4646556)
