Local complexities for empirical risk minimization

DOI10.1007/978-3-540-27819-1_19MaRDI QIDQ4680882zbMATH OpenOpenAlexFDO

Authors Peter L. Bartlett, Shahar Mendelson, Petra Philips

Publication date 13 June 2005

Published in Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/b98522

zbMATH Keywords

concentration inequalitiesdata-dependent complexityempirical risk minimizationgeneralization boundsisomorphic coordinate projectionsStatistical learning theory

Mathematics Subject Classification ID

Computational learning theory (68Q32)

Recommendations

• Empirical minimization
• Local Rademacher complexities and oracle inequalities in risk minimization. (2004 IMS Medallion Lecture). (With discussions and rejoinder)
• Sharper lower bounds on the performance of the empirical risk minimization algorithm
• Lower Bounds for the Empirical Minimization Algorithm
• Risk bounds for statistical learning

Cited in

(20)

• Learning bounds of ERM principle for sequences of time-dependent samples
• Bayesian fractional posteriors
• Model selection by resampling penalization
• Set structured global empirical risk minimizers are rate optimal in general dimensions
• Local Rademacher complexities and oracle inequalities in risk minimization. (2004 IMS Medallion Lecture). (With discussions and rejoinder)
• Model selection by bootstrap penalization for classification
• Empirical risk minimization: probabilistic complexity and stepsize strategy
• On the optimality of sample-based estimates of the expectation of the empirical minimizer
• On the importance of small coordinate projections
• Asymptotics in empirical risk minimization
• Local learning estimates by integral operators
• Stability properties of empirical risk minimization over Donsker classes
• Theory of Classification: a Survey of Some Recent Advances
• Lower Bounds for the Empirical Minimization Algorithm
• Margin-adaptive model selection in statistical learning
• Local Overfitting Control via Leverages
• Local Rademacher complexity-based learning guarantees for multi-task learning
• The relationship between agnostic selective classification, active learning and the disagreement coefficient
• Diametrical risk minimization: theory and computations
• Sharper lower bounds on the performance of the empirical risk minimization algorithm

This page was built for publication: Local complexities for empirical risk minimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4680882)