Adaptive model selection using empirical complexities

DOI10.1214/AOS/1017939241MaRDI QIDQ1583890zbMATH OpenOpenAlexFDO

Authors Gábor Lugosi, Andrew B. Nobel

Publication date 6 February 2001

Published in The Annals of Statistics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1214/aos/1017939241

zbMATH Keywords

classificationpattern recognitioncurve fittingregression estimationminimum description lengthcomplexity regularization

Mathematics Subject Classification ID

Density estimation (62G07) Nonparametric regression and quantile regression (62G08) Asymptotic properties of nonparametric inference (62G20) Classification and discrimination; cluster analysis (statistical aspects) (62H30)

Recommendations

• scientific article; zbMATH DE number 1064642
• Adaptive Model Selection
• scientific article; zbMATH DE number 1911043
• Adaptive selection and validation of models of complex systems in the presence of uncertainty
• Adaptive model selection using orthogonal least squares methods
• Adaptive semi-varying coefficient model selection
• Efficient and adaptive post-model-selection estimators

Cited in

(26)

• Minimax nonparametric classification. II. Model selection for adaptation
• Model selection in nonparametric regression
• scientific article; zbMATH DE number 7370563 (Why is no real title available?)
• Scale-sensitive dimensions and skeleton estimates for classification
• Mixing strategies for density estimation.
• scientific article; zbMATH DE number 1928797 (Why is no real title available?)
• On learning multicategory classification with sample queries.
• Margin-adaptive model selection in statistical learning
• A permutation approach to validation*
• Model selection via the VC dimension
• Aggregation for Gaussian regression
• Minimax rates for conditional density estimation via empirical entropy
• On the learnability of rich function classes
• Complexity regularization via localized random penalties
• Model selection in multivariate adaptive regression splines (MARS) using information complexity as the fitness function
• Strongly universally consistent nonparametric regression and classification with privatised data
• Optimal aggregation of classifiers in statistical learning.
• On the uniform convergence of empirical norms and inner products, with application to causal inference
• Estimating composite functions by model selection
• Learning with sample dependent hypothesis spaces
• FAST RATES FOR ESTIMATION ERROR AND ORACLE INEQUALITIES FOR MODEL SELECTION
• The Loss Rank Principle for Model Selection
• scientific article; zbMATH DE number 1064642 (Why is no real title available?)
• Model selection and error estimation
• Model selection with the loss rank principle
• Theory of Classification: a Survey of Some Recent Advances

This page was built for publication: Adaptive model selection using empirical complexities

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1583890)