English

Optimal Subgradient Methods for Lipschitz Convex Optimization with Error Bounds

Optimization and Control 2025-12-17 v1

Abstract

We study the iteration complexity of Lipschitz convex optimization problems satisfying a general error bound. We show that for this class of problems, subgradient descent with either Polyak stepsizes or decaying stepsizes achieves minimax optimal convergence guarantees for decreasing distance-to-optimality. The main contribution is a novel lower-bounding argument that produces hard functions simultaneously satisfying zero-chain conditions and global error bounds.

Keywords

Cite

@article{arxiv.2512.13863,
  title  = {Optimal Subgradient Methods for Lipschitz Convex Optimization with Error Bounds},
  author = {Alex L. Wang},
  journal= {arXiv preprint arXiv:2512.13863},
  year   = {2025}
}