Frank-Wolfe Algorithm

The Frank-Wolfe algorithm is an iterative first-order optimization algorithm for constrained convex optimization, also known as the conditional gradient method, the reduced gradient algorithm, or the convex combination algorithm. It was originally proposed by Marguerite Frank and Philip Wolfe in 1956. In each iteration, the algorithm considers a linear approximation of the objective function and moves toward a minimizer of that linear function taken over the same domain.