On ergodicity of the SAGA-LD algorithm
Probability
2026-04-15 v1
Abstract
The so-called SAGA-LD algorithm is used for efficient sampling from high-dimensional distributions in machine learning. Its intricate dynamics resists standard approaches of Markov chain theory. We prove, using a model-specific method, that SAGA-LD converges to a limiting distribution and a law of large numbers holds.
Keywords
Cite
@article{arxiv.2604.12815,
title = {On ergodicity of the SAGA-LD algorithm},
author = {Miklós Rásonyi},
journal= {arXiv preprint arXiv:2604.12815},
year = {2026}
}