A martingale approach to the problem of dimensionality and performance of bayesian classifiers: asymptotic results

DOI10.1080/03610928508805140zbMath0578.62060OpenAlexW2047339420MaRDI QIDQ3700623

George E. Kokolakis

Publication date: 1985

Published in: Communications in Statistics - Theory and Methods (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1080/03610928508805140

zbMATH Keywords

Bayesian classifiersMartingale limit theoremscoherent priorsexpected probability of correct classificationincreasing feature dimensionality

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Martingales with discrete parameter (60G42) Bayesian problems; characterization of Bayes procedures (62C10)

Cites Work

• On a Measure of the Information Provided by an Experiment
• On the expected probability of correct classification
• Bayesian classification and classification performance for independent distributions (Corresp.)
• On the Peaking of the Hughes Mean Recognition Accuracy: The Resolution of an Apparent Paradox

This page was built for publication: A martingale approach to the problem of dimensionality and performance of bayesian classifiers: asymptotic results