AI Paper Atlas

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

The Neural Tangent Kernel in High Dimensions: Triple Descent and a Multi-Scale Theory of Generalization

Ben Adlam, Jeffrey Pennington

ICML 2020 · Learning theory and algorithms › Kernels and regression theory · approach: Double descent and overfitting · 32 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
Vary model parameterization across the linear and quadratic scaling transitionsNTK regression · Gaussian inputs and wide-teacher targetstest errorMixed
Add the second-layer-weight kernel component K2Full NTK · Quadratic overparameterization transitiontest error non-monotonicityHurt
Increase the number of training examples through the n0=m or n1=m vicinityNTK regression at low SNR · Learning curvestest errorHurt
Use the superabundant-width limitNTK regression with finite SNR · Large-width learning curvestest error learning-curve rateImproved
Use the superabundant-width limit in the noiseless caseNTK regression · Large-width learning curvestest error learning-curve rateImproved
Remove centering (ablation)NTK regression · Large-width regimetest errorMixed
Reduce σW2 so the kernel approaches K2 (ablation)Full NTK · Quadratic overparameterization transitiontest error humpHurt

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