AI Paper Atlas

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

Efficient Statistical Tests: A Neural Tangent Kernel Approach

Sheng Jia, Ehsan Nezhadarya, Yuhuai Wu, Jimmy Ba

ICML 2021 · Learning theory and algorithms › Kernels and regression theory · approach: Neural tangent kernel analysis · 7 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 shift-invariant cosine first layer (SCNTK) instead of ReLU CNTK (ablation)NTK kernel for MMD two-sample tests · MNIST DCGAN shift (Table 3)successful rejection rate (avg): 0.807 vs 0.782Improved
use shift-invariant cosine first layer (SCNTK) instead of ReLU CNTK (ablation)NTK kernel for MMD two-sample tests · CIFAR10 vs CIFAR10.1 (Table 3)successful rejection rate: 0.805 vs 0.742Improved
use SCNTK random-feature approximation instead of exact NTK or Monte-Carlo NTK (ablation)SCNTK · MNIST DCGAN shift (Table 3)successful rejection rate (avg): 0.807 vs 0.814 exact, 0.809 MCNo clear effect
replace shift-invariant NTK kernel with naive Laplace kernel in pixel space (ablation)two-sample test kernel · MNIST DCGAN shift (Table 3)successful rejection rate (avg): 0.437 vs 0.807Hurt
increase network channel width from 100 to 300 (ablation)SCNTK for MNIST two-sample test · MNIST (Table 1)empirical average test power: 0.18 to 0.81Improved
use shift-invariant SCNTK KDE instead of ReLU CNTK KDE for outlier detection (ablation)KDE-based OOD detection · CIFAR10 vs SVHN (Table 5)AUROC: 0.85 vs 0.71 (CIFAR10 inlier); 0.80 vs 0.51 (SVHN inlier)Improved
fixed SCNTK kernel (no kernel training) vs optimized deep kernel MMD-D on MNIST DCGAN shiftMMD two-sample test · MNIST DCGAN shift (Table 2)successful rejection rate (avg): 0.807 vs 0.91 for MMD-DHurt
fixed SCNTK kernel vs optimized deep kernel MMD-D on CIFAR10 vs CIFAR10.1MMD two-sample test · CIFAR10 vs CIFAR10.1 (Table 2)successful rejection rate: 0.805 vs 0.744Improved
fixed SCNTK kernel vs optimized bandwidth Gaussian MMD-OMMD two-sample test · MNIST and CIFAR10 (Table 2)successful rejection rate: MNIST avg 0.807 vs 0.572; CIFAR 0.805 vs 0.316Improved
use shift-invariant random-feature Gaussian-style first layer and gradient-based kernel vs fixed Gaussian kernel on untrained autoencoder features under dataset shiftsMMD two-sample tests on MNIST/CIFAR10 with injected shifts · Gaussian noise, rotation/translation, adversarial shifts (Figure 2)dataset shift detection accuracy: more than 2x improvement reportedImproved
fixed SCNTK on class-imbalance shift vs MMD-UAE baselineMMD two-sample tests · imbalanced dataset shift (Figure 2)dataset shift detection accuracyNo clear effect

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