Efficient algorithms for learning functions with bounded variation

DOI10.1016/S0890-5401(03)00164-0MaRDI QIDQ1887165zbMATH OpenOpenAlexFDO

Authors Philip M. Long

Publication date 23 November 2004

Published in Information and Computation (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/s0890-5401(03)00164-0

zbMATH Keywords

Computational learning theoryStatistical learning theoryNonparametric regressionBounded variationSample complexity

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Classification and discrimination; cluster analysis (statistical aspects) (62H30) Computational learning theory (68Q32)

Recommendations

• Improved bounds about on-line learning of smooth functions of a single variable
• Improved bounds about on-line learning of smooth-functions of a single variable
• On the learnability of rich function classes
• Bounds on the Number of Examples Needed for Learning Functions
• Characterizations of learnability for classes of \(\{0,\dots,n\}\)-valued functions

Cites work

• scientific article; zbMATH DE number 51427 (Why is no real title available?)
• scientific article; zbMATH DE number 3436645 (Why is no real title available?)
• scientific article; zbMATH DE number 3195517 (Why is no real title available?)
• A generalization of Sauer's lemma
• A theory of the learnable
• Bounds on the Number of Examples Needed for Learning Functions
• Convergence of stochastic processes
• Covering numbers for real-valued function classes
• Decision theoretic generalizations of the PAC model for neural net and other learning applications
• Distribution inequalities for the binomial law
• Efficient distribution-free learning of probabilistic concepts
• Equivalence of models for polynomial learnability
• General bounds on the number of examples needed for learning probabilistic concepts
• Learnability and the Vapnik-Chervonenkis dimension
• Neural Network Learning
• Predicting \(\{ 0,1\}\)-functions on randomly drawn points
• Prediction, learning, uniform convergence, and scale-sensitive dimensions
• Scale-sensitive dimensions, uniform convergence, and learnability
• The complexity of learning according to two models of a drifting environment
• The importance of convexity in learning with squared loss
• Toward efficient agnostic learning

Cited in

(3)

• scientific article; zbMATH DE number 7568237 (Why is no real title available?)
• An incremental learning algorithm for function approximation
• Improved bounds about on-line learning of smooth functions of a single variable

This page was built for publication: Efficient algorithms for learning functions with bounded variation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1887165)