Asymptotic error bounds for kernel-based Nyström low-rank approximation matrices

DOI10.1016/j.jmva.2013.05.006zbMath1349.62262OpenAlexW1967099866MaRDI QIDQ391804

Chii-Ruey Hwang, Su-Yun Huang, Lo-Bin Chang, Zhi-Dong Bai

Publication date: 13 January 2014

Published in: Journal of Multivariate Analysis (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.jmva.2013.05.006

zbMATH Keywords

Nyström approximationasymptotic error boundkernel Gram matrixspectrum decompositionWishart random matrix

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Random matrices (probabilistic aspects) (60B20) Learning and adaptive systems in artificial intelligence (68T05) Limit theorems in probability theory (60F99)

Related Items (2)

The smallest eigenvalues of random kernel matrices: asymptotic results on the min kernel ⋮ Feature uncertainty bounds for explicit feature maps and large robust nonlinear SVM classifiers

Uses Software

• ElemStatLearn
• RSVM

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• CUR matrix decompositions for improved data analysis
• Support-vector networks
• Robust Kernel Principal Component Analysis
• 10.1162/15324430152748218
• Uniform Design: Theory and Application
• Fast Monte Carlo Algorithms for Matrices I: Approximating Matrix Multiplication
• Fast Monte Carlo Algorithms for Matrices II: Computing a Low-Rank Approximation to a Matrix
• Fast Monte Carlo Algorithms for Matrices III: Computing a Compressed Approximate Matrix Decomposition
• Matrix theory. Basic results and techniques
• Multicategory proximal support vector machine classifiers

This page was built for publication: Asymptotic error bounds for kernel-based Nyström low-rank approximation matrices