Adaptive model selection using empirical complexities

DOI10.1214/AOS/1017939241zbMath0962.62034OpenAlexW3123495432MaRDI QIDQ1583890

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 fittingminimum description lengthregression estimationcomplexity regularization

Mathematics Subject Classification ID

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

Related Items (15)

Complexity regularization via localized random penalties ⋮ Optimal aggregation of classifiers in statistical learning. ⋮ Learning with sample dependent hypothesis spaces ⋮ Model selection in nonparametric regression ⋮ Minimax rates for conditional density estimation via empirical entropy ⋮ Unnamed Item ⋮ On learning multicategory classification with sample queries. ⋮ On the uniform convergence of empirical norms and inner products, with application to causal inference ⋮ Aggregation for Gaussian regression ⋮ Theory of Classification: a Survey of Some Recent Advances ⋮ Strongly universally consistent nonparametric regression and classification with privatised data ⋮ A permutation approach to validation* ⋮ Scale-sensitive dimensions and skeleton estimates for classification ⋮ Mixing strategies for density estimation. ⋮ On the learnability of rich function classes

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