AI Paper Atlas

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

Over-Alignment vs Over-Fitting: The Role of Feature Learning Strength in Generalization

Taesun Yeom, Taehyeok Ha, Jaeho Lee

ICML 2026 · Learning theory and algorithms › Kernels and regression theory · approach: Statistical perspectives on generalization · 0 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 an intermediate output multiplier (optimal FLS) instead of default scale (ablation)ResNet50 · CIFAR-100peak test accuracy (%): 53.57 -> 59.76Improved
increase FLS beyond optimum (smaller output multiplier below optimum) (ablation)VGG19, ResNet18/34/50 · CIFAR-100peak test accuracyHurt
decrease FLS (larger output multiplier) (ablation)VGG19, ResNet18/34/50 · CIFAR-100peak test accuracyHurt
harder dataset (higher effective dimensionality 32 -> 128) raises the benefit of tuning FLS (ablation)ResNet18 · BigGAN dog datasettest accuracy gap to optimal FLSImproved
stop training by minimum validation loss instead of peak test accuracy (ablation)ResNet-18 · BigGAN dog dataset (edim=128)optimal output multiplierNo clear effect
scale output multiplier with width and dataset size per theory (c* ~ n^-2 h^-1)5-layer vanilla CNN · BigGAN dataset (edim=128)optimal output multiplierImproved

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