Diversity Sampling is an Implicit Regularization for Kernel Methods

DOI10.1137/20M1320031zbMath1468.62251arXiv2002.08616OpenAlexW3131344617MaRDI QIDQ4999358

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

Publication date: 6 July 2021

Published in: SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2002.08616

zbMATH Keywords

regularizationkerneldeterminantal point processNyström

Mathematics Subject Classification ID

Sampling theory, sample surveys (62D05) Point processes (e.g., Poisson, Cox, Hawkes processes) (60G55)

Related Items (4)

Nyström landmark sampling and regularized Christoffel functions ⋮ Fast Deterministic Approximation of Symmetric Indefinite Kernel Matrices with High Dimensional Datasets ⋮ On sampling determinantal and Pfaffian point processes on a quantum computer ⋮ Determinantal Point Processes Implicitly Regularize Semiparametric Regression Problems

Cites Work

• Unnamed Item
• On selecting a maximum volume sub-matrix of a matrix and related problems
• On majorization and Schur products
• Eigenvalue inequalities for principal submatrices
• The incomplete Cholesky-conjugate gradient method for the iterative solution of systems of linear equations
• Monte Carlo with determinantal point processes
• Just interpolate: kernel ``ridgeless regression can generalize
• Determinantal Point Processes for Machine Learning
• Matrix approximation and projective clustering via volume sampling
• Input Sparsity Time Low-rank Approximation via Ridge Leverage Score Sampling
• Does learning require memorization? a short tale about a long tail
• Concentration of Lipschitz Functionals of Determinantal and Other Strong Rayleigh Measures

This page was built for publication: Diversity Sampling is an Implicit Regularization for Kernel Methods