FrankWolfe.jl: a high-performance and flexible toolbox for Frank-Wolfe algorithms and Conditional Gradients
Mathieu Besan\c{c}on, Alejandro Carderera, Sebastian Pokutta
TL;DR
FrankWolfe.jl is a Julia-based open-source toolbox that offers flexible, high-performance implementations of various Frank-Wolfe and Conditional Gradient algorithms for constrained optimization, supporting easy extension and integration.
Contribution
It introduces a versatile, efficient, and extensible Julia package for first-order constrained optimization algorithms, leveraging Julia's features and MathOptInterface.
Findings
Supports multiple Frank-Wolfe variants
Ensures high performance and flexibility
Facilitates easy extension and integration
Abstract
We present FrankWolfe.jl, an open-source implementation of several popular Frank-Wolfe and Conditional Gradients variants for first-order constrained optimization. The package is designed with flexibility and high-performance in mind, allowing for easy extension and relying on few assumptions regarding the user-provided functions. It supports Julia's unique multiple dispatch feature, and interfaces smoothly with generic linear optimization formulations using MathOptInterface.jl.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Optimization Algorithms Research · Matrix Theory and Algorithms · Sparse and Compressive Sensing Techniques