AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Informative Features for Model Comparison

Wittawat Jitkrittum, Heishiro Kanagawa, Patsorn Sangkloy, James Hays, Bernhard Schölkopf, Arthur Gretton

NeurIPS 2018 · Learning theory and algorithms › Prediction and decision losses · approach: Adaptive testing and experiments · 12 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
Increase Rel-UME test locations from J10 to J40 (ablation)Rel-UME · CelebA GAN comparison 4 (S, N, RN)rejection rate: 0.57 -> 1.0Improved
Increase test locations from J10 to J20 (ablation)Rel-UME · CelebA GAN comparison 4 (S, N, RN)rejection rate: 0.57 -> 0.97Improved
Increase test locations from J20 to J40 (ablation)Rel-UME · CelebA GAN comparison 4 (S, N, RN)rejection rate: 0.97 -> 1.0Improved
Use optimized local test locations and kernel bandwidth rather than the Rel-MMD median-heuristic bandwidthRel-UME · Blobstest powerImproved
Increase the number of test locations from J=1 to J=5 (ablation)Rel-UME · Blobstest powerImproved
Use density and log-density-gradient information rather than sample-only comparisonRel-FSSD · RBM, epsilon=0.35, n=2000test powerImproved
Increase test locations from J=1 to J=5 (ablation)Rel-UME · CelebA GAN comparison 4 (S, N, RN)rejection rate: 0.57 -> 1.0Improved
Use a calibrated statistical threshold rather than treating raw FID ordering as a testRelative model comparison · CelebA GAN comparisons 1 and 2false rejection rate: 0.53; 0.7Improved
Train the LSGAN from 15 to 17 epochsLSGAN · MNIST digit 6relative goodness-of-fitImproved
Train the LSGAN from 15 to 17 epochsLSGAN · MNIST digits 3 and 9relative goodness-of-fitHurt
Use LSGAN rather than WGAN-GP after ten epochsMNIST GAN comparison · MNISTrelative goodness-of-fitImproved
Use LSGAN rather than the original GAN after 40 epochsMNIST GAN comparison · MNIST digits 1 and 5relative goodness-of-fitImproved

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