A universal well-calibrated algorithm for on-line classification

MaRDI QIDQ3093196zbMATH OpenFDO

Authors Vladimir Vovk

Publication date 12 October 2011

Full work available at URL http://www.jmlr.org/papers/v5/vovk04a.html

zbMATH Keywords

on-line predictiontransductive confidence machine

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Analysis of algorithms (68W40)

Recommendations

• Universal well-calibrated algorithm for on-line classification.
• Well-calibrated predictions from on-line compression models
• Criterion of calibration for transductive confidence machine with limited feedback
• Well-calibrated predictions from online compression models
• On Bayes methods for on-line Boolean prediction

Cited in

(9)

• Classifying under computational resource constraints: anytime classification using probabilistic estimators
• Online phenotype discovery based on minimum classification error model
• scientific article; zbMATH DE number 2040738 (Why is no real title available?)
• Universal well-calibrated algorithm for on-line classification.
• Algorithmic Learning Theory
• Criterion of calibration for transductive confidence machine with limited feedback
• A Boolean measure of similarity
• Criterion of calibration for transductive confidence machine with limited feedback
• Well-calibrated predictions from on-line compression models

This page was built for publication: A universal well-calibrated algorithm for on-line classification

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3093196)