Speculate-correct error bounds for \(k\)-nearest neighbor classifiers

DOI10.1007/s10994-019-05814-1zbMath1447.62069arXiv1410.2500OpenAlexW2963785180WikidataQ127659329 ScholiaQ127659329MaRDI QIDQ2008639

Xu Tian, Lingjie Weng, Eric T. Bax

Publication date: 26 November 2019

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

Full work available at URL: https://arxiv.org/abs/1410.2500

zbMATH Keywords

error boundsgeneralizationnearest neighbors

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Order statistics; empirical distribution functions (62G30)

Uses Software

• ElemStatLearn
• NetKit

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• The tail of the hypergeometric distribution
• Probability Inequalities for the Sum of Independent Random Variables
• A theory of the learnable
• Distribution-free inequalities for the deleted and holdout error estimates
• Validation of $k$-Nearest Neighbor Classifiers
• Learning Theory and Kernel Machines
• Probability Inequalities for Sums of Bounded Random Variables
• On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities

This page was built for publication: Speculate-correct error bounds for \(k\)-nearest neighbor classifiers