Papers › Markov Chain Score Ascent: A Unifying Framework of Variational Inference with...

Markov Chain Score Ascent: A Unifying Framework of Variational Inference with Markovian Gradients

13 Jun 2022arXiv:2206.06295archive 2025-07-28

Kyurae Kim, Jisu Oh, Jacob R. Gardner, Adji Bousso Dieng, HongSeok Kim

Minimizing the inclusive Kullback-Leibler (KL) divergence with stochastic gradient descent (SGD) is challenging since its gradient is defined as an integral over the posterior. Recently, multiple methods have been proposed to run SGD with biased gradient estimates obtained from a Markov chain. This paper provides the first non-asymptotic convergence analysis of these methods by establishing their mixing rate and gradient variance. To do this, we demonstrate that these methods-which we collectively refer to as Markov chain score ascent (MCSA) methods-can be cast as special cases of the Markov chain gradient descent framework. Furthermore, by leveraging this new understanding, we develop a novel MCSA scheme, parallel MCSA (pMCSA), that achieves a tighter bound on the gradient variance. We demonstrate that this improved theoretical result translates to superior empirical performance.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

red-portal/klpqvi.jl officialmentioned in paper report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Variational Inference

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SGD

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections