This repository contains several Frank-Wolfe (a.k.a. Conditional Gradient) algorithms implemented in Python. A sister repository implemented in Julia can be found here.

The Frank–Wolfe algorithm is an iterative first-order optimization algorithm for constrained convex optimization. Also known as the conditional gradient method, [1] reduced gradient algorithm …

Implementation of the Frank-Wolfe algorithm (aka conditional gradient method) for minimizing any convex function with linear constraints. File FrankWolfe.py includes the frank_wolfe() class for …

We present here the Frank-Wolfe algorithm that solves the given optimization, which is also called the conditional gradient method. Start with w0 2 B. For t = 1; 2; ::T. Intuitively, at each step, …

Nov 25, 2022 · The purpose of this survey is to serve both as a gentle introduction and a coherent overview of state-of-the-art Frank--Wolfe algorithms, also called conditional gradient …

Jul 30, 2021 · A very versatile and simple optimization method for projection-free optimization that promotes sparsity. Why? Constraints and Sparsity help interpretability and explainability. …

Dec 15, 2021 · It is also known as the “gradient and interpolation” algorithm or sometimes the “conditional gradient method” as it utilizes a simplex method of comparing an initial feasible …

Herein we describe the conditional-gradient method for solving P , also called the Frank-Wolfe method. This method is one of the cornerstones of opti-mization, and was one of the first …

We show a general method to lazify various conditional gradient algorithms, which in actual computations leads to several orders of magnitude of speedup in wall-clock time.

Jan 25, 2021 · We analyze the conditional gradient method, also known as Frank–Wolfe method, for constrained multiobjective optimization. The constraint set is assumed to be convex and …