English

A note on diffusion limits for stochastic gradient descent

Machine Learning 2022-10-21 v1 Optimization and Control Probability

Abstract

In the machine learning literature stochastic gradient descent has recently been widely discussed for its purported implicit regularization properties. Much of the theory, that attempts to clarify the role of noise in stochastic gradient algorithms, has widely approximated stochastic gradient descent by a stochastic differential equation with Gaussian noise. We provide a novel rigorous theoretical justification for this practice that showcases how the Gaussianity of the noise arises naturally.

Keywords

Cite

@article{arxiv.2210.11257,
  title  = {A note on diffusion limits for stochastic gradient descent},
  author = {Alberto Lanconelli and Christopher S. A. Lauria},
  journal= {arXiv preprint arXiv:2210.11257},
  year   = {2022}
}

Comments

8 pages

R2 v1 2026-06-28T04:05:15.011Z