English

Revisiting the Polyak step size

Optimization and Control 2022-08-03 v2

Abstract

This paper revisits the Polyak step size schedule for convex optimization problems, proving that a simple variant of it simultaneously attains near optimal convergence rates for the gradient descent algorithm, for all ranges of strong convexity, smoothness, and Lipschitz parameters, without a-priory knowledge of these parameters.

Keywords

Cite

@article{arxiv.1905.00313,
  title  = {Revisiting the Polyak step size},
  author = {Elad Hazan and Sham Kakade},
  journal= {arXiv preprint arXiv:1905.00313},
  year   = {2022}
}
R2 v1 2026-06-23T08:54:18.498Z