English

A Probabilistically Motivated Learning Rate Adaptation for Stochastic Optimization

Machine Learning 2021-02-23 v1

Abstract

Machine learning practitioners invest significant manual and computational resources in finding suitable learning rates for optimization algorithms. We provide a probabilistic motivation, in terms of Gaussian inference, for popular stochastic first-order methods. As an important special case, it recovers the Polyak step with a general metric. The inference allows us to relate the learning rate to a dimensionless quantity that can be automatically adapted during training by a control algorithm. The resulting meta-algorithm is shown to adapt learning rates in a robust manner across a large range of initial values when applied to deep learning benchmark problems.

Keywords

Cite

@article{arxiv.2102.10880,
  title  = {A Probabilistically Motivated Learning Rate Adaptation for Stochastic Optimization},
  author = {Filip de Roos and Carl Jidling and Adrian Wills and Thomas Schön and Philipp Hennig},
  journal= {arXiv preprint arXiv:2102.10880},
  year   = {2021}
}
R2 v1 2026-06-23T23:23:29.102Z