AI Paper Atlas

Research map / Learning theory and algorithms / Kernels and regression theory

Composite Goodness-of-fit Tests with Kernels

Oscar Key, Arthur Gretton, François-Xavier Briol, Tamara Fernandez

JMLR 2025 · Learning theory and algorithms › Kernels and regression theory · approach: Kernel two-sample testing

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 parametric instead of wild bootstrap for MMD test (ablation)MMD composite test · Gaussian model, d=1 (type I error and power)type I error / powerImproved
use parametric instead of wild bootstrap (ablation)MMD composite test · Gaussian model, d=1, n=100time per test (ms): 1ms -> 5msHurt
use KSD instead of MMDcomposite goodness-of-fit test · Gaussian model, d=1, Student-t alternativepowerImproved
increase dimension dMMD composite test · Gaussian vs multivariate tpowerImproved
increase dimension dKSD composite test · Gaussian vs multivariate tpowerHurt
use proposed MMD tests instead of non-asymptotic MMD testMMD composite test · 1D Gaussian, known variancepowerImproved
use tilted kernel in KSD test (ablation)KSD composite test · Huber contamination, d=1robustness to corruption: not robust -> robust to >6\% corruptionImproved
use specialised Gaussianity tests instead of MMD composite testGaussianity testing · Student-t alternative, varying nupowerImproved
choose lengthscale l=2 by grid search instead of median heuristic (ablation)KSD composite test · Gaussianity test vs Student-tpowerImproved
increase p of kernel exponential family (ablation)density model on galaxies data · Galaxies density fittest rejection: rejects p=1,2,3; not p=4,5,25Improved

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