English

Functional Central Limit Theorem and Strong Law of Large Numbers for Stochastic Gradient Langevin Dynamics

Probability 2023-08-01 v2 Machine Learning Optimization and Control

Abstract

We study the mixing properties of an important optimization algorithm of machine learning: the stochastic gradient Langevin dynamics (SGLD) with a fixed step size. The data stream is not assumed to be independent hence the SGLD is not a Markov chain, merely a \emph{Markov chain in a random environment}, which complicates the mathematical treatment considerably. We derive a strong law of large numbers and a functional central limit theorem for SGLD.

Keywords

Cite

@article{arxiv.2210.02092,
  title  = {Functional Central Limit Theorem and Strong Law of Large Numbers for Stochastic Gradient Langevin Dynamics},
  author = {Attila Lovas and Miklós Rásonyi},
  journal= {arXiv preprint arXiv:2210.02092},
  year   = {2023}
}

Comments

16 pages