AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Kernel-Based Tests for Likelihood-Free Hypothesis Testing

Patrik Robert Gerber, Tianze Jiang, Yury Polyanskiy, Rui Sun

NeurIPS 2023 · Learning theory and algorithms › Sample complexity · approach: Sample complexity of ranking and selection · 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
use learned-kernel MMD test instead of classifier-based and other benchmark testskernel-based likelihood-free test · CIFAR-10 vs DDPM mixed alternative, n_tr=1920rejection rate / error probabilityImproved
add the thresholding trick to the additive statistic (ablation)MMD-based test · CIFAR-10 vs DDPM source detectiontest powerNo clear effect
use MMD-M with threshold t_opt in place of other statisticsMMD-M · Higgs-Boson discoveryexpected significance of discoveryImproved
increase simulated sample size n and test sample size m on log scalekernel-based test · CIFAR-10 vs DDPM and Higgstotal probability of errorImproved
use other benchmarks (thresholded MMD, MMD-O, LBI, RFM)likelihood-free tests · CIFAR-10 vs DDPMtest powerHurt

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