A Vector-Contraction Inequality for Rademacher Complexities

DOI10.1007/978-3-319-46379-7_1zbMATH Open1478.68296OpenAlexW2962708723MaRDI QIDQ2830263FDOQ2830263

Authors Andreas Maurer

Publication date 9 November 2016

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

Full work available at URL https://arxiv.org/abs/1605.00251

zbMATH Keywords

contraction inequalityRademacher complexities

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05) Inequalities; stochastic orderings (60E15) Computational learning theory (68Q32)

Abstract: The contraction inequality for Rademacher averages is extended to Lipschitz functions with vector-valued domains, and it is also shown that in the bounding expression the Rademacher variables can be replaced by arbitrary iid symmetric and sub-gaussian variables. Example applications are given for multi-category learning, K-means clustering and learning-to-learn.

Recommendations

• 10.1162/153244303321897690
• scientific article; zbMATH DE number 1804106
• Approximation error bounds via Rademacher's complexity
• Rademacher inequalities with applications
• On the $L_p$ norm of the Rademacher projection and related inequalities
• Rademacher Margin Complexity
• The Rademacher Complexity of Linear Transformation Classes
• Estimates of the approximation error using Rademacher complexity: Learning vector-valued functions
• The Khinchin Inequality for Generalized Rademacher Functions
• A \(\Phi \)-entropy contraction inequality for Gaussian vectors

Cites work

• scientific article; zbMATH DE number 49190 (Why is no real title available?)
• scientific article; zbMATH DE number 1448976 (Why is no real title available?)
• $K$-Dimensional Coding Schemes in Hilbert Spaces
• 10.1162/15324430260185628
• 10.1162/153244303321897690
• 10.1162/1532443041424300
• Concentration inequalities. A nonasymptotic theory of independence
• Empirical margin distributions and bounding the generalization error of combined classifiers
• On the Performance of Clustering in Hilbert Spaces
• On the best constants in the Khinchin inequality
• Optimal rates for the regularized least-squares algorithm
• Regularization techniques for learning with matrices
• The benefit of multitask representation learning
• Transfer bounds for linear feature learning

Cited in

(14)

• Graphical convergence of subgradients in nonconvex optimization and learning
• Handling concept drift via model reuse
• Weakly convex optimization over Stiefel manifold using Riemannian subgradient-type methods
• Compressive sensing and neural networks from a statistical learning perspective
• Multi-kernel learning for multi-label classification with local Rademacher complexity
• Weight normalized deep neural networks
• Algorithmic Learning Theory
• Convergence analysis of machine learning algorithms for the numerical solution of mean field control and games. I: The ergodic case
• From inexact optimization to learning via gradient concentration
• scientific article; zbMATH DE number 7370541 (Why is no real title available?)
• On strong consistency of kernel \(k\)-means: a Rademacher complexity approach
• Also for \(k\)-means: more data does not imply better performance
• Robust \(k\)-means clustering for distributions with two moments
• Estimates of the approximation error using Rademacher complexity: Learning vector-valued functions

This page was built for publication: A Vector-Contraction Inequality for Rademacher Complexities

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2830263)