Universal well-calibrated algorithm for on-line classification.

DOI10.1007/B12006MaRDI QIDQ5305863zbMATH OpenOpenAlexFDO

Authors Vladimir Vovk

Publication date 23 March 2010

Published in Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/b12006

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Online algorithms; streaming algorithms (68W27)

Recommendations

• A 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

(4)

• A universal well-calibrated algorithm for on-line classification
• Criterion of calibration for transductive confidence machine with limited feedback
• Criterion of calibration for transductive confidence machine with limited feedback
• Well-calibrated predictions from on-line compression models

This page was built for publication: 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 Q5305863)