AI Paper Atlas

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

GILBO: One Metric to Measure Them All

Alexander A Alemi, Ian Fischer

NeurIPS 2018 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Disentangled and discrete latent models · 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
Measure model complexity with GILBO alongside FIDGANs on MNIST · MNISTFIDMixed
Compare GAN and VAE complexity at the same FIDGANs versus VAEs · MNISTGILBOHurt
Use GILBO to distinguish models with equal FIDCelebA GANs · CelebAGILBO: ∼41 nats; ∼70 nats; ∼104 natsMixed
Replace the amortized encoder with separately optimized per-image encodersCelebA GANs · CelebAGILBO: 41 -> 87; 70 -> 111; 104 -> 155Improved
Use a variational encoder approximation to estimate generative mutual informationGANs · CelebAGILBONo clear effect
Use the same encoder architecture and training procedure across compared modelsGILBO comparisons · CelebAGILBO reproducibility: below 2% of the mean GILBOImproved

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