On the stochastic complexity of learning realizable and unrealizable rules

MaRDI QIDQ1900982zbMATH OpenFDO

Authors Ronny Meir, Neri Merhav

Publication date 29 November 1995

Published in Machine Learning (Search for Journal in Brave)

zbMATH Keywords

stochastic complexitymodel selection methods

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• scientific article; zbMATH DE number 4068049
• scientific article; zbMATH DE number 3971958
• A decision-theoretic extension of stochastic complexity and its applications to learning
• Stochastic complexity and the mdl principle
• Stochastic complexity in learning

Cited in

(9)

• A learning criterion for stochastic rules
• An information theoretic tradeoff between complexity and accuracy.
• An axiomatization of learning rules when counterfactuals are not observed
• Suboptimal behavior of Bayes and MDL in classification under misspecification
• Most sequences are stochastic
• Bayesian model learning based on predictive entropy
• Mutual information, metric entropy and cumulative relative entropy risk
• scientific article; zbMATH DE number 4068049 (Why is no real title available?)
• Bayesian predictiveness, exchangeability and sufficientness in bacterial taxonomy

This page was built for publication: On the stochastic complexity of learning realizable and unrealizable rules

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1900982)