On the consistency of the empirical risk minimization principle based on algorithmic stability

MaRDI QIDQ3610132zbMATH OpenFDO

Authors Deqiang Zhou, Bin Zou

Publication date 6 March 2009

zbMATH Keywords

algorithmic stabilitychange-one error estimateempirical risk minimization principle

Mathematics Subject Classification ID

Mechanization of proofs and logical operations (03B35)

Recommendations

• Learning theory: stability is sufficient for generalization and necessary and sufficient for consistency of empirical risk minimization
• STABILITY RESULTS IN LEARNING THEORY
• Stability and generalization of learning algorithm: a new framework of stability
• 10.1162/153244302760200704
• Learnability, stability and uniform convergence

Cited in

(2)

• Learning theory: stability is sufficient for generalization and necessary and sufficient for consistency of empirical risk minimization
• On the Stability of Empirical Risk Minimization in the Presence of Multiple Risk Minimizers

This page was built for publication: On the consistency of the empirical risk minimization principle based on algorithmic stability

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3610132)