AI Paper Atlas

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

Efficient Numerical Integration in Reproducing Kernel Hilbert Spaces via Leverage Scores Sampling

Antoine Chatalic, Nicolas Schreuder, Ernesto De Vito, Lorenzo Rosasco

JMLR 2025 · Learning theory and algorithms › Kernels and regression theory · approach: RKHS kernel methods · 5 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 approximate ridge leverage score sampling instead of uniform sampling of nodes (ablation)Nystrom-based RKHS quadrature · OpenML datasets, Gaussian kernelworst-case error vs number of nodes mImproved
Use approximate ridge leverage score sampling instead of uniform sampling of nodes (ablation)Nystrom-based RKHS quadrature · Periodic Sobolev spaces (d=1,s=1 and d=2,s=3)worst-case errorNo clear effect
Use approximate ridge leverage score sampling instead of uniform sampling of nodes (ablation)Nystrom-based RKHS quadrature · OpenML datasets, Laplacian kernelworst-case errorNo clear effect
Use proposed quadrature instead of greedy and DPP baselines at equal runtimeNystrom-based RKHS quadrature · Periodic Sobolev spaceserror vs runtime tradeoffImproved
Use proposed quadrature instead of greedy and DPP baselines at fixed node count mNystrom-based RKHS quadrature · Periodic Sobolev spaceserror at fixed mHurt
Use proposed quadrature instead of other randomized and greedy baselines at equal runtimeNystrom-based RKHS quadrature · OpenML datasets, Gaussian kernelerror vs runtime tradeoffImproved
Use greedy det(K_m) maximization (space-filling) instead of data-adaptive selectionGreedy baseline · OpenML datasets, Gaussian kernelaccuracyHurt

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