English

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

Optimization and Control 2017-10-23 v1

Abstract

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 ff has uniformly continuous (on bounded sets) Fr\'echet derivative ff'. We introduce the notion of the curvature constant of order σ(1,2]\sigma\in (1,2] and obtain the rate O(1kσ1)O(\frac{1}{k^{\sigma-1}}) of convergence of the Frank-Wolfe algorithm. In particular, this rate reduces to O(1kν)O(\frac{1}{k^{\nu}}) if ff' is ν\nu-H\"older continuous for ν(0,1]\nu\in (0,1], and to O(1k)O(\frac{1}{k}) if ff' 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.

Keywords

Cite

@article{arxiv.1710.07367,
  title  = {Convergence Analysis of the Frank-Wolfe Algorithm and Its Generalization in Banach Spaces},
  author = {Hong-Kun Xu},
  journal= {arXiv preprint arXiv:1710.07367},
  year   = {2017}
}

Comments

27 pages

R2 v1 2026-06-22T22:19:59.446Z