A Vector-Contraction Inequality for Rademacher Complexities

DOI10.1007/978-3-319-46379-7_1zbMath1478.68296arXiv1605.00251MaRDI QIDQ2830263

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 inequality; Rademacher complexities

Mathematics Subject Classification ID

62H30: Classification and discrimination; cluster analysis (statistical aspects)

68Q32: Computational learning theory

60E15: Inequalities; stochastic orderings

68T05: Learning and adaptive systems in artificial intelligence

Related Items

Unnamed Item, Convergence Analysis of Machine Learning Algorithms for the Numerical Solution of Mean Field Control and Games I: The Ergodic Case, Weakly Convex Optimization over Stiefel Manifold Using Riemannian Subgradient-Type Methods, Graphical Convergence of Subgradients in Nonconvex Optimization and Learning, Multi-kernel learning for multi-label classification with local Rademacher complexity, Also for \(k\)-means: more data does not imply better performance, Robust \(k\)-means clustering for distributions with two moments, On strong consistency of kernel \(k\)-means: a Rademacher complexity approach, Compressive sensing and neural networks from a statistical learning perspective, From inexact optimization to learning via gradient concentration, Handling concept drift via model reuse

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Empirical margin distributions and bounding the generalization error of combined classifiers
• Transfer bounds for linear feature learning
• Optimal rates for the regularized least-squares algorithm
• Concentration Inequalities
• 10.1162/15324430260185628
• On the Performance of Clustering in Hilbert Spaces
• On the best constants in the Khinchin inequality
• 10.1162/1532443041424300
• 10.1162/153244303321897690
• $K$-Dimensional Coding Schemes in Hilbert Spaces