English

Modeling AdaGrad, RMSProp, and Adam with Integro-Differential Equations

Machine Learning 2025-10-14 v2 Numerical Analysis Numerical Analysis Optimization and Control

Abstract

In this paper, we propose a continuous-time formulation for the AdaGrad, RMSProp, and Adam optimization algorithms by modeling them as first-order integro-differential equations. We perform numerical simulations of these equations, along with stability and convergence analyses, to demonstrate their validity as accurate approximations of the original algorithms. Our results indicate a strong agreement between the behavior of the continuous-time models and the discrete implementations, thus providing a new perspective on the theoretical understanding of adaptive optimization methods.

Keywords

Cite

@article{arxiv.2411.09734,
  title  = {Modeling AdaGrad, RMSProp, and Adam with Integro-Differential Equations},
  author = {Carlos Heredia},
  journal= {arXiv preprint arXiv:2411.09734},
  year   = {2025}
}

Comments

47 pages, 15 figures

R2 v1 2026-06-28T20:00:23.835Z