Paperlane

no. 14 · Friday 13 November 2026

On ergodicity of the SAGA-LD algorithm

Miklós Rásonyi

math.PR · v2

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.

comments
Several small corrections
fields
Probability
pdf ↗ page arXiv:2604.12815 ↗