Model selection by bootstrap penalization for classification

DOI10.1007/s10994-006-7679-yzbMath1470.62083OpenAlexW2053894133MaRDI QIDQ2384135

Magalie Fromont

Publication date: 20 September 2007

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

Full work available at URL: https://doi.org/10.1007/s10994-006-7679-y

zbMATH Keywords

classificationexponential inequalitymodel selectionminimax riskoracle inequalitybootstrap penalty

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30)

Related Items (3)

Bootstrap model selection for possibly dependent and heterogeneous data ⋮ Model selection in utility-maximizing binary prediction ⋮ A permutation approach to validation*

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Some limit theorems for empirical processes (with discussion)
• Risk bounds for statistical learning
• Bootstrapping general empirical measures
• On a second-order asymptotic property of the Bayesian bootstrap mean
• Bounds for the uniform deviation of empirical measures
• Estimation of dependences based on empirical data. Transl. from the Russian by Samuel Kotz
• Minimum contrast estimators on sieves: Exponential bounds and rates of convergence
• Exchangeably weighted bootstraps of the general empirical process
• Sphere packing numbers for subsets of the Boolean \(n\)-cube with bounded Vapnik-Chervonenkis dimension
• Smooth discrimination analysis
• On prediction of individual sequences
• A large sample study of the Bayesian bootstrap
• Optimal aggregation of classifiers in statistical learning.
• Weak convergence and empirical processes. With applications to statistics
• Local Rademacher complexities and oracle inequalities in risk minimization. (2004 IMS Medallion Lecture). (With discussions and rejoinder)
• Weighted sums of certain dependent random variables
• On the density of families of sets
• Local Rademacher complexities
• Theory of Classification: a Survey of Some Recent Advances
• Minimum complexity density estimation
• A sharp concentration inequality with applications
• Rademacher penalties and structural risk minimization
• Learning Theory
• Concept learning using complexity regularization
• Learning by canonical smooth estimation. I. Simultaneous estimation
• On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
• Model selection and error estimation

This page was built for publication: Model selection by bootstrap penalization for classification