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

arXiv: https://arxiv.org/abs/2104.06675 · HTML: https://mlsanity.com/paper/2104.06675/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Apr 2021.

## Built on by (most cited first, 8 of 8)

- [Learning with Combinatorial Optimization Layers: a Probabilistic Approach](https://mlsanity.com/paper/2207.13513/) (2022)
- [Interpretable Neural Networks with Frank-Wolfe: Sparse Relevance Maps and Relevance Orderings](https://mlsanity.com/paper/2110.08105/) (2021)
- [Convex mixed-integer optimization with Frank-Wolfe methods](https://mlsanity.com/paper/2208.11010/) (2022)
- [SAIF: Sparse Adversarial and Imperceptible Attack Framework](https://mlsanity.com/paper/2212.07495/) (2022)
- [Scalable Frank-Wolfe on Generalized Self-concordant Functions via Simple Steps](https://mlsanity.com/paper/2105.13913/) (2021)
- [Accelerated Nonnegative Tensor Completion via Integer Programming](https://mlsanity.com/paper/2211.15770/) (2022)
- [Scalable DC Optimization via Adaptive Frank-Wolfe Algorithms](https://mlsanity.com/paper/2507.17545/) (2025)
- [An Enhanced Zeroth-Order Stochastic Frank-Wolfe Framework for Constrained Finite-Sum Optimization](https://mlsanity.com/paper/2501.07201/) (2025)

## Abstract (arXiv)

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.