Saved in:
Bibliographic Details
Main Author: Rásonyi, Miklós
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.12815
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914471783432192
author Rásonyi, Miklós
author_facet Rásonyi, Miklós
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_12815
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle On ergodicity of the SAGA-LD algorithm
Rásonyi, Miklós
Probability
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.
title On ergodicity of the SAGA-LD algorithm
topic Probability
url https://arxiv.org/abs/2604.12815