Constant Stepsize Local GD for Logistic Regression: Acceleration by Instability

Michael Crawshaw; Blake Woodworth; Mingrui Liu

2025 ICML ICML 2025

Constant Stepsize Local GD for Logistic Regression: Acceleration by Instability

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Michael Crawshaw, Blake Woodworth, Mingrui Liu

Topics

Machine Learning > Core Methods > Classification Machine Learning > Optimization & Theory > Optimization

Keywords

logistic regression convergence rate heterogeneous data step size local gradient descent instability

Download PDF