English

Stochastic Adaptive Gradient Descent Without Descent

Machine Learning 2025-09-19 v1 Optimization and Control Machine Learning

Abstract

We introduce a new adaptive step-size strategy for convex optimization with stochastic gradient that exploits the local geometry of the objective function only by means of a first-order stochastic oracle and without any hyper-parameter tuning. The method comes from a theoretically-grounded adaptation of the Adaptive Gradient Descent Without Descent method to the stochastic setting. We prove the convergence of stochastic gradient descent with our step-size under various assumptions, and we show that it empirically competes against tuned baselines.

Keywords

Cite

@article{arxiv.2509.14969,
  title  = {Stochastic Adaptive Gradient Descent Without Descent},
  author = {Jean-François Aujol and Jérémie Bigot and Camille Castera},
  journal= {arXiv preprint arXiv:2509.14969},
  year   = {2025}
}
R2 v1 2026-07-01T05:43:54.380Z