Scale-sensitive dimensions and skeleton estimates for classification

DOI10.1016/S0166-218X(98)00013-4zbMath0934.62065MaRDI QIDQ1265744

Gábor Lugosi, Márta Horváth

Publication date: 27 April 2000

Published in: Discrete Applied Mathematics (Search for Journal in Brave)

zbMATH Keywords

skeletons; binary classification; empirical risk; regression functions

Mathematics Subject Classification ID

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

Related Items

Optimal aggregation of classifiers in statistical learning.

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Estimation of dependences based on empirical data. Transl. from the Russian by Samuel Kotz
• Decision theoretic generalizations of the PAC model for neural net and other learning applications
• A result of Vapnik with applications
• Efficient distribution-free learning of probabilistic concepts
• Adaptive model selection using empirical complexities
• Fat-shattering and the learnability of real-valued functions
• On the density of families of sets
• Learnability and the Vapnik-Chervonenkis dimension
• Efficient agnostic learning of neural networks with bounded fan-in
• Covering numbers for real-valued function classes
• Scale-sensitive dimensions, uniform convergence, and learnability
• Function Learning from Interpolation
• A metric entropy bound is not sufficient for learnability
• Learning by canonical smooth estimation. I. Simultaneous estimation
• Learning by canonical smooth estimation. II. Learning and choice of model complexity
• On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
• Convergence of stochastic processes