An improved analysis of the Rademacher data-dependent bound using its self bounding property

DOI10.1016/J.NEUNET.2013.03.017MaRDI QIDQ459446zbMATH OpenOpenAlexWikidataFDO

Authors Luca Oneto, Alessandro Ghio, Davide Anguita, Sandro Ridella

Publication date 9 October 2014

Published in Neural Networks (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.neunet.2013.03.017

zbMATH Keywords

error estimationRademacher complexityconcentration of measuredata-dependent bounds

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• 10.1162/153244303768966111
• Local Rademacher complexities
• scientific article; zbMATH DE number 1804114
• 10.1162/153244303321897690
• scientific article; zbMATH DE number 1804106

Cites work

• scientific article; zbMATH DE number 4170917 (Why is no real title available?)
• scientific article; zbMATH DE number 1332320 (Why is no real title available?)
• 10.1162/153244303321897690
• A sharp concentration inequality with applications
• An improved analysis of the Rademacher data-dependent bound using its self bounding property
• Aspects of discrete mathematics and probability in the theory of machine learning
• Concentration inequalities using the entropy method
• Learning pattern classification-a survey
• Local Rademacher complexities
• Local Rademacher complexity: sharper risk bounds with and without unlabeled samples
• Model selection and error estimation
• Rademacher penalties and structural risk minimization
• Some limit theorems for empirical processes (with discussion)
• Structural risk minimization over data-dependent hierarchies

Cited in

(5)

• Tikhonov, Ivanov and Morozov regularization for support vector machine learning
• An improved analysis of the Rademacher data-dependent bound using its self bounding property
• Selective Rademacher penalization and reduced error pruning of decision trees
• Local Rademacher complexity: sharper risk bounds with and without unlabeled samples
• Percolation centrality via Rademacher Complexity

Describes a project that uses

Uses Software

• M@cbeth

This page was built for publication: An improved analysis of the Rademacher data-dependent bound using its self bounding property

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q459446)