Lower Bounds for the Empirical Minimization Algorithm

DOI10.1109/TIT.2008.926323MaRDI QIDQ3604755zbMATH OpenOpenAlexFDO

Authors Shahar Mendelson

Publication date 24 February 2009

Published in IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1109/tit.2008.926323

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Generalized linear models (logistic models) (62J12) Analysis of algorithms (68W40)

Recommendations

• Sharper lower bounds on the performance of the empirical risk minimization algorithm
• Empirical minimization
• Learning Theory
• On the optimality of sample-based estimates of the expectation of the empirical minimizer
• Learning without concentration

Cited in

(13)

• Learning Theory
• Stability properties of empirical risk minimization over Donsker classes
• Empirical minimization
• Sharper lower bounds on the performance of the empirical risk minimization algorithm
• A deterministic learning approach based on discrepancy.
• Semi-supervised AUC optimization based on positive-unlabeled learning
• Obtaining fast error rates in nonconvex situations
• On the optimality of the aggregate with exponential weights for low temperatures
• Empirical risk minimization is optimal for the convex aggregation problem
• General nonexact oracle inequalities for classes with a subexponential envelope
• Aggregation via empirical risk minimization
• Optimal convergence rate of the universal estimation error
• On the optimality of sample-based estimates of the expectation of the empirical minimizer

This page was built for publication: Lower Bounds for the Empirical Minimization Algorithm

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3604755)