AI Paper Atlas

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

Moment Matching Denoising Gibbs Sampling

Mingtian Zhang, Alex Hawkins-Hooker, Brooks Paige, David Barber

NeurIPS 2023 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Posterior sampling with diffusion guidance · 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
use analytical full x-tilde-dependent covariance instead of learned diagonal or isotropic covariance in Gibbs sampling (ablation)Moment matching denoising Gibbs sampler · 2D mixture of Gaussians, Swiss roll, two ringsMMDImproved
replace KL-trained learned diagonal covariance with analytic moment-matched covariance (ablation)Gibbs sampler on MNIST · MNISTsample quality (visual)Improved
use x-tilde-dependent diagonal covariance instead of x-tilde-independent isotropic covariance (ablation)Gibbs sampler on MNIST · MNISTbackground cleanliness (visual)Improved
learned diagonal covariance trained by KL minimization versus DSM objective (ablation)MNIST energy/denoising model · MNISTtraining stabilityHurt
vary noise level sigma among 0.3, 0.5, 0.8 (ablation)Single-noise Gibbs sampler · MNISTvisual sample qualityMixed
increase number of Rademacher samples for diagonal Hessian estimate (1, 10, 100) (ablation)Diagonal covariance estimator · CIFAR-10covariance estimation quality (visual)Improved
run more Gibbs steps with single noise level sigma=0.3 (ablation)Single-noise Gibbs sampler · CIFAR-10FIDHurt
run Gibbs chains longer on MNISTSingle-noise Gibbs sampler · MNISTmode coverageHurt
use multiple noise levels instead of a single noise level (ablation)Moment matching Gibbs sampler · CIFAR-10FIDImproved
replace annealed Langevin dynamics with multi-level Gibbs sampling (3 steps per level, 3 Rademacher samples)Pretrained noise-conditioned score network · CIFAR-10FID and Inception scoreNo clear effect
add final denoising step returning clean-distribution mean after last noise levelMulti-level Gibbs sampler · CIFAR-10FIDImproved

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