English

Accelerated Almost-Sure Convergence Rates for Nonconvex Stochastic Gradient Descent using Stochastic Learning Rates

Optimization and Control 2021-11-11 v2 Machine Learning

Abstract

Large-scale optimization problems require algorithms both effective and efficient. One such popular and proven algorithm is Stochastic Gradient Descent which uses first-order gradient information to solve these problems. This paper studies almost-sure convergence rates of the Stochastic Gradient Descent method when instead of deterministic, its learning rate becomes stochastic. In particular, its learning rate is equipped with a multiplicative stochasticity, producing a stochastic learning rate scheme. Theoretical results show accelerated almost-sure convergence rates of Stochastic Gradient Descent in a nonconvex setting when using an appropriate stochastic learning rate, compared to a deterministic-learning-rate scheme. The theoretical results are verified empirically.

Keywords

Cite

@article{arxiv.2110.12634,
  title  = {Accelerated Almost-Sure Convergence Rates for Nonconvex Stochastic Gradient Descent using Stochastic Learning Rates},
  author = {Theodoros Mamalis and Dusan Stipanovic and Petros Voulgaris},
  journal= {arXiv preprint arXiv:2110.12634},
  year   = {2021}
}
R2 v1 2026-06-24T07:08:52.094Z