Gradient Descent Converges Arbitrarily Fast for Logistic Regression via Large and Adaptive Stepsizes

Ruiqi Zhang; Jingfeng Wu; Peter Bartlett

2025 ICML ICML 2025

Gradient Descent Converges Arbitrarily Fast for Logistic Regression via Large and Adaptive Stepsizes

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.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Mathematics & Optimization

Authors

Ruiqi Zhang, Jingfeng Wu, Peter Bartlett

Topics

Machine Learning > Optimization & Theory > Optimization Mathematics & Optimization > Optimization > Continuous Optimization

Keywords

logistic regression gradient descent margin iteration complexity step size risks

Download PDF