Covering numbers of Gaussian reproducing kernel Hilbert spaces

DOI10.1016/j.jco.2011.01.005zbMath1221.68195MaRDI QIDQ555034

Thomas Kühn

Publication date: 22 July 2011

Published in: Journal of Complexity (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.jco.2011.01.005

zbMATH Keywords

learning theory; covering numbers; small deviations; Gaussian RKHS; smooth Gaussian processes

Mathematics Subject Classification ID

68Q32: Computational learning theory

68T05: Learning and adaptive systems in artificial intelligence

Related Items

Learning Rates for Classification with Gaussian Kernels, Small ball probabilities for smooth Gaussian fields and tensor products of compact operators, Variance-based regularization with convex objectives, \( L_2\)-small ball asymptotics for Gaussian random functions: a survey, Small deviations for a family of smooth Gaussian processes, A closer look at covering number bounds for Gaussian kernels, Adaptive learning rates for support vector machines working on data with low intrinsic dimension, Sharp estimates for the covering numbers of the Weierstrass fractal kernel, Approximations of semicontinuous functions with applications to stochastic optimization and statistical estimation, Balancing principle in supervised learning for a general regularization scheme, On the equivalence of probability spaces, Modal additive models with data-driven structure identification

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Reproducing kernel Hilbert spaces associated with analytic translation-invariant Mercer kernels
• Fast rates for support vector machines using Gaussian kernels
• Metric entropy and the small ball problem for Gaussian measures
• Approximation, metric entropy and small ball estimates for Gaussian measures
• Eigenvalue distribution of compact operators
• The covering number in learning theory
• On the mathematical foundations of learning
• Tricks or Treats with the Hilbert Matrix
• Learning Theory
• Support Vector Machines
• Capacity of reproducing kernel spaces in learning theory
• An Explicit Description of the Reproducing Kernel Hilbert Spaces of Gaussian RBF Kernels
• Small Deviations of Smooth Stationary Gaussian Processes
• Generalization performance of regularization networks and support vector machines via entropy numbers of compact operators
• Small ball probabilities for smooth Gaussian fields and tensor products of compact operators
• Theory of Reproducing Kernels