FrankWolfe.jl: A High-Performance and Flexible Toolbox for Frank–Wolfe Algorithms and Conditional Gradients

DOI10.1287/IJOC.2022.1191MaRDI QIDQ5058004zbMATH OpenOpenAlexFDO

Authors Mathieu Besançon, Alejandro Carderera, Sebastian Pokutta

Publication date 1 December 2022

Published in INFORMS Journal on Computing (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2104.06675

zbMATH Keywords

first-order methodsnonlinear programmingoptimization software

Mathematics Subject Classification ID

Mathematical programming (90Cxx)

Recommendations

• A unified analysis of stochastic gradient‐free Frank–Wolfe methods
• Frank-Wolfe and friends: a journey into projection-free first-order optimization methods
• Fast and scalable Lasso via stochastic Frank-Wolfe methods with a convergence guarantee
• A Momentum-Guided Frank-Wolfe Algorithm
• Frank-Wolfe style algorithms for large scale optimization
• Frank--Wolfe Methods with an Unbounded Feasible Region and Applications to Structured Learning
• A modified Frank-Wolfe algorithm and its convergence properties
• On the Frank-Wolfe algorithm for non-compact constrained optimization problems
• Generalized stochastic Frank-Wolfe algorithm with stochastic ``substitute gradient for structured convex optimization
• Restarting Frank-Wolfe: faster rates under Hölderian error bounds

Cites work

• A Stochastic Approximation Method
• ARPACK Users' Guide
• Complexity of linear minimization and projection on some sets
• Exact matrix completion via convex optimization
• scientific article; zbMATH DE number 845714 (Why is no real title available?)
• scientific article; zbMATH DE number 3293978 (Why is no real title available?)
• Julia: a fresh approach to numerical computing
• JuMP: a modeling language for mathematical optimization
• Some comments on Wolfe's ‘away step’
• Stochastic conditional gradient methods: from convex minimization to submodular maximization
• The Power of Convex Relaxation: Near-Optimal Matrix Completion
• Why Are Big Data Matrices Approximately Low Rank?

Cited in

(12)

• EAGO.jl: easy advanced global optimization in Julia
• FrankWolfe.jl
• FrankWolfe.jl: a high-performance and flexible toolbox for Frank-Wolfe algorithms and Conditional Gradients
• Scalable Frank-Wolfe on generalized self-concordant functions via simple steps
• Flexible differentiable optimization via model transformations
• Improved algorithms and novel applications of the FrankWolfe.jl library
• Convex mixed-integer optimization with Frank-Wolfe methods
• Tropical Fréchet means: a polyhedral approach to exact optimization
• Tropical Fréchet means
• High-precision linear minimization is no slower than projection
• Flexible block-iterative analysis for the Frank-Wolfe algorithm
• Graph isomorphism: mixed-integer convex optimization from first-order methods

Describes a project that uses

Uses Software

• Convex.jl
• Julia
• Optim
• JSOSolvers.jl
• MathOptInterface.jl
• ARPACK
• MovieLens
• JuMP
• GitHub

This page was built for publication: FrankWolfe.jl: A High-Performance and Flexible Toolbox for Frank–Wolfe Algorithms and Conditional Gradients

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5058004)