AI Paper Atlas

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

Neural Tangent Kernel Maximum Mean Discrepancy

Xiuyuan Cheng, Yao Xie

NeurIPS 2021 · Learning theory and algorithms › Kernels and regression theory · approach: Neural tangent kernel analysis · 6 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 NTK-MMD instead of the strongest listed baseline, C2ST-L with Adam for 10 epochstwo-sample testing · Gaussian mixture Example 1, d=10test power: 14.1 (87.8) -> 7.1; 38.4 (100.0) -> 9.6; 76.4 (100.0) -> 13.7; 92.9 (100.0) -> 17.9Hurt
Use NTK-MMD instead of C2ST-L with Adam for 1 epochtwo-sample testing · Gaussian mixture Example 2, d=10test power: 48.5 -> 34.3; 92.8 -> 68.9; 99.5 -> 88.8; 100.0 -> 95.9Mixed
Use NTK-MMD instead of C2ST-S with SGD for 1 epochtwo-sample testing · Gaussian mixture Example 1, d=10test power: 6.0 -> 7.1; 10.6 -> 9.6; 10.8 -> 13.7; 14.8 -> 17.9Improved
Use NTK-MMD instead of C2ST-S with SGD or Adam for 1 epochtwo-sample testing · Gaussian mixture Example 2, d=10test power: NTK-MMD: 34.3, 68.9, 88.8, 95.9; C2ST-S (Adam): 21.8, 62.2, 79.4, 94.6; C2ST-S (SGD): 7.4, 22.7, 35.3, 54.9Improved
Increase the number of training samples processed during online trainingNTK-MMD · Gaussian covariance shifttesting powerImproved
Replace the full NTK-MMD computation with test-only bootstrap calibrationasymmetric NTK-MMD · Gaussian covariance shifttesting powerNo clear effect
Use NTK-MMD instead of Gaussian MMD or Hotelling's T-testtwo-sample testing · Gaussian mean shift in R^100testing powerMixed
Use NTK-MMD instead of Hotelling's T-testchange-point detection · MSRC-12 human activity sequencedetection statisticImproved

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