AI Paper Atlas

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

Precise Learning Curves and Higher-Order Scalings for Dot-product Kernel Regression

Lechao Xiao, Hong Hu, Theodor Misiakiewicz, Yue Lu, Jeffrey Pennington

NeurIPS 2022 · Learning theory and algorithms › Kernels and regression theory · approach: Double descent and overfitting · 1 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
Increase the spectral gap Gap between consecutive kernel eigenvalue levels (2, 8, 32, 128) (ablation)Dot-product kernel ridgeless regression · Synthetic sphere data, d=24test error learning curveMixed
Use a small spectral gap (Gap=8 or 2) (ablation)Dot-product kernel ridgeless regression · Synthetic sphere datalearning curve monotonicityImproved
Increase input dimension d toward infinity (ablation)Theoretical learning-curve prediction · Second peak r=2, 32 runsgap between simulation and predictionImproved
Replace dot-product kernel with one-hidden-layer CNN kernelLearning-curve theory · d0=20, p=6agreement of prediction with simulationNo 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