AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

Graph-accelerated Markov Chain Monte Carlo using Approximate Samples

Leo L. Duan, Anirban Bhattacharya

JMLR 2025 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Stochastic gradient MCMC · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add graph-accelerated jumps using 100 approximate samples to random-walk MetropolisRandom-walk Metropolis · Banana-shaped posterior (2D)effective sample size per iteration of theta_1: 0.16% -> 6.1%Improved
increase dimension p from 103 to 2003 at fixed m=1600 (ablation)Graph-accelerated sampler · Simulated latent Gaussian modelMH acceptance rate of graph jump: around 26% -> around 17%Hurt
increase approximate sample size m from 200 to 1600 at p=503 (ablation)Graph-accelerated sampler · Simulated latent Gaussian modelMH acceptance rate of graph jumpNo clear effect
use greedy-optimized (r, kappa) or optimized random-walk graph instead of default spanning tree graph (ablation)Graph-accelerated sampler · Gaussian mixture examplemixing (traceplot)Improved
replace Gibbs sampler with graph-accelerated samplerLatent Gaussian count model · Power outage dataautocorrelation: autocorrelation near 40% at lag 100 -> small after lag 60Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy