Projection-free accelerated method for convex optimization

DOI10.1080/10556788.2020.1734806zbMath1501.90067MaRDI QIDQ5038178

Jefferson G. Melo, Renato D. C. Monteiro, Max L. N. Gonçalves

Publication date: 29 September 2022

Published in: Optimization Methods and Software (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1080/10556788.2020.1734806

zbMATH Keywords

conditional gradient method; first-order methods; accelerated method; projection-free method

Mathematics Subject Classification ID

90C22: Semidefinite programming

90C25: Convex programming

90C06: Large-scale problems in mathematical programming

49M37: Numerical methods based on nonlinear programming

Related Items

Frank--Wolfe Methods with an Unbounded Feasible Region and Applications to Structured Learning, Approximate Douglas-Rachford algorithm for two-sets convex feasibility problems, Inexact gradient projection method with relative error tolerance

Cites Work

• Unnamed Item
• Smooth minimization of non-smooth functions
• An adaptive accelerated first-order method for convex optimization
• On lower complexity bounds for large-scale smooth convex optimization
• Conditional gradient algorithms for norm-regularized smooth convex optimization
• A generalized conditional gradient method and its connection to an iterative shrinkage method
• Introductory lectures on convex optimization. A basic course.
• A conditional gradient method with linear rate of convergence for solving convex linear systems
• Conditional Gradient Sliding for Convex Optimization
• Duality Between Subgradient and Conditional Gradient Methods
• An Accelerated HPE-Type Algorithm for a Class of Composite Convex-Concave Saddle-Point Problems
• Convergence Rates for Conditional Gradient Sequences Generated by Implicit Step Length Rules
• An accelerated non-Euclidean hybrid proximal extragradient-type algorithm for convex–concave saddle-point problems
• Conditional Gradient Algorithmsfor Rank-One Matrix Approximations with a Sparsity Constraint