English

A geometric interpretation of stochastic gradient descent using diffusion metrics

Machine Learning 2020-02-19 v1 General Relativity and Quantum Cosmology Differential Geometry Machine Learning

Abstract

Stochastic gradient descent (SGD) is a key ingredient in the training of deep neural networks and yet its geometrical significance appears elusive. We study a deterministic model in which the trajectories of our dynamical systems are described via geodesics of a family of metrics arising from the diffusion matrix. These metrics encode information about the highly non-isotropic gradient noise in SGD. We establish a parallel with General Relativity models, where the role of the electromagnetic field is played by the gradient of the loss function. We compute an example of a two layer network.

Keywords

Cite

@article{arxiv.1910.12194,
  title  = {A geometric interpretation of stochastic gradient descent using diffusion metrics},
  author = {R. Fioresi and P. Chaudhari and S. Soatto},
  journal= {arXiv preprint arXiv:1910.12194},
  year   = {2020}
}
R2 v1 2026-06-23T11:56:04.486Z