Corpus ID: 233231567

FrankWolfe.jl: a high-performance and flexible toolbox for Frank-Wolfe algorithms and Conditional Gradients

@inproceedings{Besanccon2021FrankWolfejlAH,
  title={FrankWolfe.jl: a high-performance and flexible toolbox for Frank-Wolfe algorithms and Conditional Gradients},
  author={M. Besanccon and Alejandro Carderera and Sebastian Pokutta},
  year={2021}
}
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. 
1 Citations

Figures and Tables from this paper

Simple steps are all you need: Frank-Wolfe and generalized self-concordant functions

References

SHOWING 1-10 OF 31 REFERENCES
Blended Conditional Gradients: the unconditioning of conditional gradients
Linearly Convergent Frank-Wolfe with Backtracking Line-Search.
Lazifying Conditional Gradient Algorithms
On the Global Linear Convergence of Frank-Wolfe Optimization Variants
JuMP: A Modeling Language for Mathematical Optimization
Optim: A mathematical optimization package for Julia
Variance-Reduced and Projection-Free Stochastic Optimization
Complexity of Linear Minimization and Projection on Some Sets
Convex Optimization in Julia
Proximal Gradient Algorithms: Applications in Signal Processing
...
1
2
3
4
...