AI Paper Atlas

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

Training-Free Determination of Network Width via Neural Tangent Kernel

Tatsumi Sunada, Toshihiko Yamasaki, Atsuto Maki

ICLR 2026 · Learning theory and algorithms › Kernels and regression theory · approach: Neural tangent kernel analysis

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 smallest NTK eigenvalue saturation at initialization to pick width instead of training sweepsDNN, CNN, ResNet width selection · Diabetes, California Housing, MNIST, CIFAR-10 (regression)agreement of predicted width with test-loss saturationImproved
vary optimizer, learning rate and initialization (ablation)cardinal width on DNN · UCI Diabetescardinal widthNo clear effect
compute mu_min on a subsample of the data (ablation)cardinal width estimate · DNN on California Housingrelative saturation across widthsNo clear effect
use the method outside lazy training (feature-learning regime)cardinal width · experiments without lazy-training constraintsmu_min saturation vs test-loss saturationNo clear effect
compare test loss to NTK bound mu_min^-2two-layer ReLU on synthetic regression · make_regression, widths 16 to 1024test loss vs mu_minMixed

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