On expected error of randomized Nyström kernel regression

DOI10.2298/FIL2011871TMaRDI QIDQ5081273zbMATH OpenOpenAlexFDO

Authors Aleksandar Trokicić, Branimir Todorović

Publication date 14 June 2022

Published in Filomat (Search for Journal in Brave)

Full work available at URL https://doi.org/10.2298/fil2011871t

zbMATH Keywords

kernel regressionkernel matrixrandomized SVDrandom featuresNyström method

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Learning and adaptive systems in artificial intelligence (68T05) Randomized algorithms (68W20) Analysis of algorithms (68W40)

Recommendations

• Randomized Nyström features for fast regression: an error analysis
• Approximate minimization of the regularized expected error over kernel models
• Exponential bounds of mean error for the kernel estimate of regression functions
• scientific article; zbMATH DE number 25609
• Iteratively reweighted least square for kernel expectile regression with random features
• Generalization error rates in kernel regression: the crossover from the noiseless to noisy regime*
• Nonparametric kernel methods with errors-in-variables: constructing estimators, computing them, and avoiding common mistakes
• scientific article; zbMATH DE number 1866535
• The effect of the regularity of the error process on the performance of kernel regression estimators

Cites work

• scientific article; zbMATH DE number 6276143 (Why is no real title available?)
• An introduction to support vector machines and other kernel-based learning methods.
• CUR matrix decompositions for improved data analysis
• Finding structure with randomness: probabilistic algorithms for constructing approximate matrix decompositions
• Gaussian processes for machine learning.
• Improved analysis of the subsampled randomized Hadamard transform
• Matrix concentration inequalities via the method of exchangeable pairs
• User-friendly tail bounds for sums of random matrices

Cited in

(1)

• Randomized Nyström features for fast regression: an error analysis

This page was built for publication: On expected error of randomized Nyström kernel regression

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5081273)