Stability properties of empirical risk minimization over Donsker classes

zbMATH Open1222.68156MaRDI QIDQ3174051FDOQ3174051

Authors: Alexander Rakhlin, Andrea Caponnetto 

Publication date: 12 October 2011

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

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

zbMATH Keywords

stabilityempirical processesempirical risk minimizationDonsker classes

Mathematics Subject Classification ID

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

Cited In (8)

• Concentration inequalities for empirical processes of linear time series
• Title not available (Why is that?)
• On the Stability of Empirical Risk Minimization in the Presence of Multiple Risk Minimizers
• Diametrical risk minimization: theory and computations
• Efficient sampling from time-varying log-concave distributions
• Analysis of error propagation in particle filters with approximation
• On the optimality of sample-based estimates of the expectation of the empirical minimizer
• 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)