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

DOI10.1016/j.neunet.2013.03.017zbMath1296.68137OpenAlexW2031690114WikidataQ30616773 ScholiaQ30616773MaRDI QIDQ459446

Davide Anguita, Sandro Ridella, Luca Oneto, Alessandro Ghio

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 estimationconcentration of measureRademacher complexitydata-dependent bounds

Mathematics Subject Classification ID

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

Related Items (4)

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

Uses Software

• M@cbeth

Cites Work

• Unnamed Item
• Unnamed Item
• An improved analysis of the Rademacher data-dependent bound using its self bounding property
• Some limit theorems for empirical processes (with discussion)
• Concentration inequalities using the entropy method
• Local Rademacher complexity: sharper risk bounds with and without unlabeled samples
• Aspects of discrete mathematics and probability in the theory of machine learning
• Local Rademacher complexities
• A sharp concentration inequality with applications
• Rademacher penalties and structural risk minimization
• Structural risk minimization over data-dependent hierarchies
• Learning pattern classification-a survey
• 10.1162/153244303321897690
• Model selection and error estimation

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