AI Paper Atlas

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

Understanding VAEs in Fisher-Shannon Plane

Huangjie Zheng, Jiangchao Yao, Ya Zhang, Ivor W. Tsang, Jia Wang

AAAI 2019 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Hierarchical VAEs and posterior collapse · 16 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 Fisher-information regularization with F=20VAE, yielding FAE · MNISTtest NLL: 85.56 -> 79.30Improved
Set Fisher-information constraint to F=0 instead of F=20 (ablation)FAE · MNISTtest NLL: 79.30 -> 83.24Hurt
Use Fisher-information constraint F=20 rather than F=0.1 (ablation)FAE · Reversed MNISTtrain NLL: 96.67 -> 94.48Improved
Use Fisher-information constraint F=20 rather than F=0.1 (ablation)FAE · Reversed MNISTtest NLL: 108.37 -> 164.56Hurt
Lower the Fisher-information constraint from F=20 to F=0.1 (ablation)FAE · Reversed MNISTtest NLL: 164.56 -> 108.37Improved
Increase the Fisher-information constraint (ablation)FAE · MNIST and SVHN reconstructionreconstruction detail and fidelityImproved
Increase the Fisher-information constraint (ablation)FAE · MNIST latent representationdisentanglementImproved
Increase entropy power by reducing F (ablation)FAE · Reversed MNISTgeneralization: 164.56 -> 108.37Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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