Rademacher Chaos Complexities for Learning the Kernel Problem

DOI10.1162/NECO_A_00028MaRDI QIDQ3057230zbMATH OpenDBLPWikidataFDO

Authors Yiming Ying, Colin Campbell

Publication date 24 November 2010

Published in Neural Computation (Search for Journal in Brave)

zbMATH Keywords

learning Gaussian kernelsmetric entropy integralsradial basis kernels

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Refined Rademacher chaos complexity bounds with applications to the multikernel learning problem
• Learning theory of randomized Kaczmarz algorithm
• Rademacher complexity for Markov chains: applications to kernel smoothing and Metropolis-Hastings
• 10.1162/153244303321897690
• scientific article; zbMATH DE number 1804106
• Researches on Rademacher complexities in statistical learning theory: a survey
• Rademacher Margin Complexity
• Estimates of the approximation error using Rademacher complexity: Learning vector-valued functions
• Stochastic complexity in learning
• Multiple spectral kernel learning and a Gaussian complexity computation

Cites work

• 10.1162/153244303321897690
• Choosing multiple parameters for support vector machines
• Convexity, Classification, and Risk Bounds
• Fast rates for support vector machines using Gaussian kernels
• Learning Bounds for Support Vector Machines with Learned Kernels
• Learning Theory
• Learning and approximation by Gaussians on Riemannian manifolds
• Limit theorems for \(U\)-processes
• Local Rademacher complexities
• Model selection for regularized least-squares algorithm in learning theory
• Multi-kernel regularized classifiers
• Neural Network Learning
• Optimal rates for the regularized least-squares algorithm
• Rademacher averages and phase transitions in Glivenko-Cantelli classes
• Rademacher penalties and structural risk minimization
• Ranking and empirical minimization of \(U\)-statistics
• Scale-sensitive dimensions, uniform convergence, and learnability
• Shannon sampling and function reconstruction from point values
• Statistical behavior and consistency of classification methods based on convex risk minimization.

Cited in

(11)

• Generalization bounds for metric and similarity learning
• Generalization analysis of multi-modal metric learning
• On the optimal estimation of probability measures in weak and strong topologies
• Error Analysis of Coefficient-Based Regularized Algorithm for Density-Level Detection
• Refined generalization bounds of gradient learning over reproducing kernel Hilbert spaces
• U-Processes and Preference Learning
• Modeling interactive components by coordinate kernel polynomial models
• On strong consistency of kernel \(k\)-means: a Rademacher complexity approach
• Refined Rademacher chaos complexity bounds with applications to the multikernel learning problem
• Permutational Rademacher Complexity
• Towards learning optimized kernels for complex Langevin

This page was built for publication: Rademacher Chaos Complexities for Learning the Kernel Problem

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3057230)