AI Paper Atlas

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

Integral Probability Metrics Meet Neural Networks: The Radon-Kolmogorov-Smirnov Test

Seunghoon Paik, Michael Celentano, Alden Green, Ryan J. Tibshirani

JMLR 2025 · Learning theory and algorithms › Kernels and regression theory · approach: Kernel regression under shift · 9 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 RKS test instead of Gaussian kernel MMD and energy distance when P and Q differ in one directionRKS test · first four synthetic settings (pancake-shift, ball-shift, t-coord, var-one), d=2,4,8,16ROC / powerImproved
use RKS test instead of Gaussian kernel MMD and energy distance when P and Q differ in all directionsRKS test · var-all, larger dROC / powerHurt
use smoothness degree k=0 in RKS (ablation)RKS test · pancake-shiftROC / powerImproved
increase smoothness degree to k=1 (ablation)RKS test · t-coordROC / powerImproved
increase smoothness degree to k=2 or 3 (ablation)RKS test · var-oneROC / powerImproved
vary smoothness degree k=0,1,2 (ablation)RKS test · ball-shiftROC / powerNo clear effect
increase dimension d from 2 to 16 (ablation)all tests · pancake-shift, var-oneROC / powerHurt
aggregate RKS p-values over degrees k with min-rule or Fisher-rule (ablation)RKS test · five synthetic settings, d=2,4,8,16ROC / powerImproved
increase number of neurons N (overparametrization) (ablation)RKS optimization · RKS distance computationoptimization stabilityImproved

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