AI Paper Atlas

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

Learning Multi-layer Latent Variable Model via Variational Optimization of Short Run MCMC for Approximate Inference

Erik Nijkamp, Bo Pang, Tian Han, Linqi Zhou, Song-Chun Zhu, Ying Nian Wu

ECCV 2020 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Hierarchical VAEs and posterior collapse · 20 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 latent layers (L=1 to L=5) (ablation)short run MCMC inference · CelebA (64x64), K=25FID: 61.03 -> 47.95Improved
add latent layers (L=1 to L=5) (ablation)short run MCMC inference · CelebA (64x64), K=25reconstruction MSE: 0.020 -> 0.015Improved
increase inference steps from K=5 to K=25 (ablation)short run MCMC inference · CelebA (32x32), L=5FID: 82.79 -> 36.84Improved
increase inference steps from K=25 to K=400 (ablation)short run MCMC inference · CelebA (32x32), L=5FID: 36.84 -> 35.16No clear effect
increase inference steps from K=5 to K=25 (ablation)short run MCMC inference · CelebA (32x32), L=5reconstruction MSE: 0.045 -> 0.011Improved
use short run MCMC inference instead of Ladder-VAE inference network (L=5)multi-layer generator · CelebA (32x32)FID: 53.40 -> 36.84Improved
use short run MCMC inference instead of Ladder-VAE inference network (L=5)multi-layer generator · SVHN (32x32)FID: 39.26 -> 35.23Improved
use short run MCMC inference instead of Ladder-VAE inference network (L=5)multi-layer generator · SVHN (32x32)reconstruction MSE: 0.014 -> 0.011Improved
use short run MCMC inference instead of Ladder-VAE (L=1)single-layer generator · SVHN (32x32)reconstruction MSE: 0.019 -> 0.018No clear effect
use short run MCMC inference instead of VAE (L=1)single-layer generator · CelebA (32x32), L=1FID: 69.90 -> 45.74Improved
use short run MCMC inference instead of ABP (L=1)single-layer generator · SVHN (32x32), L=1FID: 49.71 -> 44.86Improved
optimize step size by gradient descent vs grid search (ablation)short run MCMC step size · SVHNstep size: 0.05No 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