AI Paper Atlas

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

Learning sparse features can lead to overfitting in neural networks

Leonardo Petrini, Francesco Cagnetta, Eric Vanden-Eijnden, Matthieu Wyart

NeurIPS 2022 · Learning theory and algorithms › Kernels and regression theory · approach: Double descent and overfitting · 8 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 lazy NTK training instead of feature learningOne-hidden-layer ReLU network · Smooth Gaussian random functions on the d-dimensional unit spheregeneralization error exponent βImproved
Use RFK lazy training instead of feature learningOne-hidden-layer ReLU network · Smooth Gaussian random functions on the d-dimensional unit spheregeneralization error exponent βImproved
Learn sparse features rather than use lazy trainingFully-connected networks on image datasets · Benchmark image datasetsrelative sensitivity to small diffeomorphismsHurt
Learn sparse features rather than use lazy trainingFully-connected networks on image datasets · Benchmark image datasetsclassification performanceHurt
Use feature learning instead of lazy trainingOne-hidden-layer ReLU network · Gaussian random functions on the d-dimensional unit sphere with insufficiently smooth targetsgeneralization error exponent βNo 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