Stability properties of empirical risk minimization over Donsker classes

MaRDI QIDQ3174051zbMATH OpenFDO

Authors Alexander Rakhlin, Andrea Caponnetto

Publication date 12 October 2011

Full work available at URL http://www.jmlr.org/papers/v7/caponnetto06a.html

zbMATH Keywords

stabilityempirical processesempirical risk minimizationDonsker classes

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Nonparametric inference (62G99)

Recommendations

• STABILITY RESULTS IN LEARNING THEORY
• Learning theory: stability is sufficient for generalization and necessary and sufficient for consistency of empirical risk minimization
• A note on stability of error bounds in statistical learning theory
• Lower Bounds for the Empirical Minimization Algorithm
• Learning Theory

Cited in

(8)

• On the optimality of sample-based estimates of the expectation of the empirical minimizer
• scientific article; zbMATH DE number 7307480 (Why is no real title available?)
• Diametrical risk minimization: theory and computations
• Analysis of error propagation in particle filters with approximation
• On the Stability of Empirical Risk Minimization in the Presence of Multiple Risk Minimizers
• Efficient sampling from time-varying log-concave distributions
• Concentration inequalities for empirical processes of linear time series
• Also for \(k\)-means: more data does not imply better performance

This page was built for publication: Stability properties of empirical risk minimization over Donsker classes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3174051)