# Convergence Analysis of the Frank-Wolfe Algorithm and Its Generalization in Banach Spaces

arXiv: https://arxiv.org/abs/1710.07367 · HTML: https://mlsanity.com/paper/1710.07367/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Oct 2017.

## Built on by (most cited first, 1 of 1)

- [Broximal Gradient Descent: A Projection-Free Sister of Projected Gradient Descent](https://mlsanity.com/paper/2605.08850/) (2026)

## Abstract (arXiv)

The Frank-Wolfe algorithm, a very first optimization method and also known as the conditional gradient method, was introduced by Frank and Wolfe in 1956. Due to its simple linear subproblems, the Frank-Wolfe algorithm has recently been received much attention for solving large-scale structured optimization problems arising from many applied areas such as signal processing and machine learning. In this paper we will discuss in detail the convergence analysis of the Frank-Wolfe algorithm in Banach spaces. Two ways of the selections of the stepsizes are discussed: the line minimization search method and the open loop rule. In both cases, we prove the convergence of the Frank-Wolfe algorithm in the case where the objective function f has uniformly continuous (on bounded sets) Fr'echet derivative f'. We introduce the notion of the curvature constant of order σ∈ (1,2] and obtain the rate O(frac1kσ-1) of convergence of the Frank-Wolfe algorithm. In particular, this rate reduces to O(frac1knu) if f' is nu-H"older continuous for nu∈ (0,1], and to O(frac1k) if f' is Lipschitz continuous. A generalized Frank-Wolfe algorithm is also introduced to address the problem of minimizing a composite objective function. Convergence of iterates of both Frank-Wolfe and generalized Frank-Wolfe algorithms are investigated.