AI Paper Atlas

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

Generalized Energy Based Models

Michael Arbel, Liang Zhou, Arthur Gretton

ICLR 2021 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Score-based generative modeling analysis · 4 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 the learned energy to sample from the latent posterior instead of sampling from the base alone (ablation)GEBM with SNGAN ConvNet · Cifar10FID: 32.03 -> 23.02Improved
Use the learned energy to sample from the latent posterior instead of sampling from the base alone (ablation)GEBM with SNGAN ConvNet · LSUNFID: 21.67 -> 15.25Improved
Use the learned energy to sample from the latent posterior instead of sampling from the base alone (ablation)GEBM with SNGAN ConvNet · CelebAFID: 6.91 -> 5.21Improved
Use the learned energy to sample from the latent posterior instead of sampling from the base alone (ablation)GEBM with SNGAN ConvNet · ImageNetFID: 19.37 -> 13.94Improved
Use KLA rather than ULA for latent-posterior sampling (ablation)GEBM with SNGAN ConvNet · Cifar10FID: 23.02 -> 24.29Hurt
Use KLA rather than ULA for latent-posterior sampling (ablation)GEBM with SNGAN ConvNet · LSUNFID: 16.23 -> 15.25Improved
Train with KALE (F) rather than direct maximum likelihoodReal NVP density model · RedWine, Whitewine, Parkinsons, Hepmass, MinibooneNLL: 11.98 -> 11.19; 13.05 -> 12.66; 14.5 -> 13.26; 24.89 -> 24.66; 42.28 -> 38.35Mixed
Train with KALE (F) rather than contrastive divergenceReal NVP density model · RedWine, Whitewine, Parkinsons, Hepmass, MinibooneNLL: 11.88 -> 11.19; 13.01 -> 12.66; 14.06 -> 13.26; 22.89 -> 24.66; 39.36 -> 38.35Mixed
Use KALE (F) rather than KALE (DV)Real NVP density model · RedWine, Whitewine, Parkinsons, Hepmass, MinibooneNLL: 11.6 -> 11.19; 12.77 -> 12.66; 13.26 -> 13.26; 26.56 -> 24.66; 46.48 -> 38.35Mixed
Rescale the energy by beta=100 for colder samplingGEBM · Image-generation tasksFIDImproved

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