AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Testing and Learning on Distributions with Symmetric Noise Invariance

Ho Chung Law, Christopher Yau, Dino Sejdinovic

NeurIPS 2017 · Learning theory and algorithms › Sample complexity · approach: Density and property estimation · 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
Test paired differences for asymmetry instead of applying ME directly to samplesTwo-sample testing with differing additive symmetric noise · Synthetic noisy χ²Type I error controlImproved
Apply ME directly to samples rather than using the paired-difference SME testTwo-sample testing with differing additive symmetric noise · Synthetic noisy χ²Type I error controlHurt
Use the PhD test at large additive noise levelsPhD two-sample test · Synthetic noisy χ²Type I error controlHurt
Use the PhD test rather than SME at small noise levelsTwo-sample testing · Synthetic noisy χ²powerImproved
Use SME rather than ME on low-level angular-momentum featuresTwo-sample testing · Higgs low-level featuresType I errorImproved
Use SME rather than ME on high-level featuresTwo-sample testing · Higgs high-level features, N=500power: 0.94 vs 1.0Hurt
Use phase features instead of Fourier embeddingsDistribution regression · Aerosol MISR1RMSE robustness to test noiseImproved
Learn discriminative frequencies with Phase NN instead of using PLRR phase featuresDistribution regression · Aerosol MISR1RMSE robustness to covariate shiftImproved
Use phase features rather than Fourier embeddingsDistribution regression · Dark Matter ML1RMSEImproved
Apply a second-level Gaussian kernel to phase features rather than approximate embeddingsDistribution regression · Dark Matter ML1RMSEMixed
Remove per-frequency normalization from Phase NN, yielding Fourier NN (ablation)Phase NN · Aerosol MISR1RMSE robustness to covariate shiftNo clear effect
Use MMD on paired differences rather than phase featuresLearning on distributions · Synthetic noisy χ² bagsinvariance to additive symmetric noiseHurt

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