Improving the sample complexity using global data

DOI10.1109/TIT.2002.1013137MaRDI QIDQ4674555zbMATH OpenFDO

Authors Shahar Mendelson

Publication date 11 May 2005

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

Full work available at URL https://doi.org/10.1109/TIT.2002.1013137

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Sampling theory, sample surveys (62D05)

Recommendations

• scientific article; zbMATH DE number 1827090
• scientific article; zbMATH DE number 1445318
• Improved bounds on the sample complexity of learning
• Local Rademacher complexities
• Distribution-dependent sample complexity of large margin learning

Cited in

(24)

• Empirical minimization
• Measuring the capacity of sets of functions in the analysis of ERM
• Distribution-free robust linear regression
• Local Rademacher complexities and oracle inequalities in risk minimization. (2004 IMS Medallion Lecture). (With discussions and rejoinder)
• Local Rademacher complexities
• scientific article; zbMATH DE number 7370625 (Why is no real title available?)
• \(\ell _{1}\)-regularized linear regression: persistence and oracle inequalities
• Multi-kernel regularized classifiers
• Fast rates for support vector machines using Gaussian kernels
• Approximating \(L_p\) unit balls via random sampling
• scientific article; zbMATH DE number 1804108 (Why is no real title available?)
• scientific article; zbMATH DE number 1827090 (Why is no real title available?)
• Fast generalization error bound of deep learning without scale invariance of activation functions
• Oracle inequalities for support vector machines that are based on random entropy numbers
• SVM Soft Margin Classifiers: Linear Programming versus Quadratic Programming
• Deep learning: a statistical viewpoint
• Revised loss bounds for the set covering machine and sample-compression loss bounds for imbalanced data
• FAST RATES FOR ESTIMATION ERROR AND ORACLE INEQUALITIES FOR MODEL SELECTION
• Direct importance estimation for covariate shift adaptation
• Learning without concentration for general loss functions
• Classification with non-i.i.d. sampling
• On the optimality of sample-based estimates of the expectation of the empirical minimizer
• Learning Bounds for Kernel Regression Using Effective Data Dimensionality
• Theory of Classification: a Survey of Some Recent Advances

This page was built for publication: Improving the sample complexity using global data

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4674555)