English

Perturbed Fenchel duality and first-order methods

Optimization and Control 2021-12-06 v7

Abstract

We show that the iterates generated by a generic first-order meta-algorithm satisfy a canonical perturbed Fenchel duality inequality. The latter in turn readily yields a unified derivation of the best known convergence rates for various popular first-order algorithms including the conditional gradient method as well as the main kinds of Bregman proximal methods: subgradient, gradient, fast gradient, and universal gradient methods.

Keywords

Cite

@article{arxiv.1812.10198,
  title  = {Perturbed Fenchel duality and first-order methods},
  author = {David H. Gutman and Javier F. Peña},
  journal= {arXiv preprint arXiv:1812.10198},
  year   = {2021}
}

Comments

26 pages

R2 v1 2026-06-23T06:56:01.512Z