Probabilities of discrepancy between minima of cross-validation, Vapnik bounds and true risks

DOI10.2478/v10006-010-0039-xzbMath1339.62003OpenAlexW1997524487MaRDI QIDQ3053683

P. Klęsk

Publication date: 29 October 2010

Published in: International Journal of Applied Mathematics and Computer Science (Search for Journal in Brave)

Full work available at URL: https://eudml.org/doc/208005

zbMATH Keywords

cross-validationgeneralizationstatistical learning theoryregression estimationmodel comparisonstructural risk minimizationgeneralization boundscomplexity selection

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08)

Uses Software

• bootstrap

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Application of structural risk minimization to multivariate smoothing spline regression estimates
• Least angle and \(\ell _{1}\) penalized regression: a review
• A result of Vapnik with applications
• Covering numbers for real-valued function classes
• The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the network
• 10.1162/153244302760200713
• Chernoff–Hoeffding Bounds for Applications with Limited Independence
• Sharpening of the Upper Bound of the Absolute Constant in the Berry–Esseen Inequality
• Advanced Lectures on Machine Learning
• Estimation of Dependences Based on Empirical Data
• Probability of error, equivocation, and the Chernoff bound
• An application of Fourier methods to the problem of sharpening the Berry-Esseen inequality
• The Accuracy of the Gaussian Approximation to the Sum of Independent Variates