AI Paper Atlas

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

Posterior Matching for Arbitrary Conditioning

Ryan Strauss, Junier Oliva

NeurIPS 2022 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Disentangled and discrete latent models · 2 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 VDVAE rather than VQ-VAE as the base model with Posterior MatchingPosterior Matching image inpainting · MNIST, Omniglot, and CelebAPSNRMixed
Apply Posterior Matching rather than VAEACTabular arbitrary conditional density estimation · Power, Gas, Hepmass, Miniboone, BSDSNRMSE: Power: 0.880 $\pm$ 0.001 -> 0.834 $\pm$ 0.001; Gas: 0.574 $\pm$ 0.033 -> 0.330 $\pm$ 0.013; Hepmass: 0.896 $\pm$ 0.001 -Improved
Apply Posterior Matching rather than VAEACTabular arbitrary conditional density estimation · Power, Gas, Hepmass, Miniboone, BSDSLL: Power: -0.042 $\pm$ 0.002 -> 0.246 $\pm$ 0.002; Gas: 2.418 $\pm$ 0.006 -> 5.964 $\pm$ 0.005; Hepmass: -10.082 $\pm$ 0.01Improved
Use VDVAE + Posterior Matching instead of ACFlow+BGImage inpainting · MNIST and CelebAPSNR: MNIST: 20.828 $\pm$ 0.031 -> 21.603 $\pm$ 0.022; CelebA: 25.723 $\pm$ 0.020 -> 27.190 $\pm$ 0.049Improved
Use VDVAE + Posterior Matching instead of ACFlow+BGImage inpainting · OmniglotPSNR: 18.838 $\pm$ 0.009 -> 18.256 $\pm$ 0.038Hurt
Replace sampling-based feature acquisition with learned lookahead posteriorsGreedy active feature acquisition · MNISTacquisition time: 68 ms $\pm$ 917 $\mu$s -> 310 $\mu$s $\pm$ 15.3 $\mu$s; 219xImproved
Use lookahead posteriors instead of sampling-based acquisitionGreedy active feature acquisition · MNISTreconstruction RMSENo clear effect

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