English

Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression

Machine Learning 2025-05-08 v2

Abstract

We analyze two variants of Local Gradient Descent applied to distributed logistic regression with heterogeneous, separable data and show convergence at the rate O(1/KR)O(1/KR) for KK local steps and sufficiently large RR communication rounds. In contrast, all existing convergence guarantees for Local GD applied to any problem are at least Ω(1/R)\Omega(1/R), meaning they fail to show the benefit of local updates. The key to our improved guarantee is showing progress on the logistic regression objective when using a large stepsize η1/K\eta \gg 1/K, whereas prior analysis depends on η1/K\eta \leq 1/K.

Keywords

Cite

@article{arxiv.2501.13790,
  title  = {Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression},
  author = {Michael Crawshaw and Blake Woodworth and Mingrui Liu},
  journal= {arXiv preprint arXiv:2501.13790},
  year   = {2025}
}

Comments

ICLR 2025

R2 v1 2026-06-28T21:15:02.055Z