Nyström landmark sampling and regularized Christoffel functions

DOI10.1007/s10994-022-06165-0OpenAlexW4223465886MaRDI QIDQ2163251

Johan A. K. Suykens, Joachim Schreurs, Michaël Fanuel

Publication date: 10 August 2022

Published in: Machine Learning (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1905.12346

zbMATH Keywords

kerneldiversitydeterminantal point processNyström

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Uses Software

• catamari

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Freedman's inequality for matrix martingales
• Determinantal processes and independence
• Matrices and n-widths
• On the Lambert \(w\) function
• The empirical Christoffel function with applications in data analysis
• Greedy algorithms for reduced bases in Banach spaces
• On some extensions of Bernstein's inequality for self-adjoint operators
• Orthogonal Series Density Estimation and the Kernel Eigenvalue Problem
• Determinantal Point Processes for Machine Learning
• Convergence Rates for Greedy Algorithms in Reduced Basis Methods
• Optimal Quadrature-Sparsification for Integral Operator Approximation
• Active Learning and Basis Selection for Kernel-Based Linear Models: A Bayesian Perspective
• Input Sparsity Time Low-rank Approximation via Ridge Leverage Score Sampling
• Online Row Sampling
• High-performance sampling of generic determinantal point processes
• Diversity Sampling is an Implicit Regularization for Kernel Methods
• Gaussian Process Landmarking on Manifolds
• Exact sampling of determinantal point processes without eigendecomposition
• Does learning require memorization? a short tale about a long tail
• Convergence rate of the data-independent $P$-greedy algorithm in kernel-based approximation
• Learning Bounds for Kernel Regression Using Effective Data Dimensionality

This page was built for publication: Nyström landmark sampling and regularized Christoffel functions