A new PAC bound for intersection-closed concept classes

DOI10.1007/S10994-006-8638-3zbMATH Open1470.68074OpenAlexW1963910319MaRDI QIDQ2384136FDOQ2384136

Authors: Peter Auer, Ronald Ortner 

Publication date: 20 September 2007

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

Full work available at URL: https://doi.org/10.1007/s10994-006-8638-3

Recommendations

• Learning Theory
• The optimal PAC bound for intersection-closed concept classes
• PAC-learning from general examples
• Trial and error: A new approach to space-bounded learning
• scientific article

zbMATH Keywords

PAC boundsintersection-closed classes

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Analysis of algorithms and problem complexity (68Q25) Computational learning theory (68Q32)

Cites Work

• On the density of families of sets
• Learnability and the Vapnik-Chervonenkis dimension
• A general lower bound on the number of examples needed for learning
• Approximating hyper-rectangles: Learning and pseudorandom sets
• Learning nested differences in the presence of malicious noise
• Predicting \(\{ 0,1\}\)-functions on randomly drawn points
• Title not available (Why is that?)
• On-line learning with malicious noise and the closure algorithm

Cited In (6)

• \(k\)-Fold unions of low-dimensional concept classes
• Trial and error: A new approach to space-bounded learning
• Learning intersection-closed classes with signatures
• Localization of VC classes: beyond local Rademacher complexities
• The optimal PAC bound for intersection-closed concept classes
• Learning Theory

This page was built for publication: A new PAC bound for intersection-closed concept classes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2384136)