mlsanityData to 7 Oct 2026

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

arXiv 2210.02092 ↗First posted 5 Oct 2022math.PR cs.LG math.OCcited by 1

Not on the map. Why?

Abstract (arXiv)

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 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.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 3 of its 21 references that are in the map. First posted on arXiv 5 Oct 2022.

Builds on

3 of 21 references.

References · 3

  1. 2014Consistency and fluctuations for stochastic gradient Langevin dynamicscited by 65
  2. 2018On stochastic gradient Langevin dynamics with dependent data streams in the logconcave casecited by 20
  3. 2019Markov chains in random environment with applications in queueing theory and machine learningcited by 3

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024Transition of α-mixing in Random Iterations with Applications in Queuing Theorycited by 0