Optimal learning with anisotropic Gaussian SVMs

DOI10.1016/J.ACHA.2021.06.004OpenAlexW3173796915MaRDI QIDQ1979927

Hanyuan Hang, Ingo Steinwart

Publication date: 3 September 2021

Published in: Applied and Computational Harmonic Analysis (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1810.02321

zbMATH Keywords

nonparametric regressionleast squares support vector machineslearning ratesanisotropic kernels

Mathematics Subject Classification ID

Computer science (68-XX) Game theory, economics, finance, and other social and behavioral sciences (91-XX)

Related Items (3)

Choosing shape parameters for regression in reproducing kernel Hilbert space and variable selection ⋮ Optimal rates of convergence for nonparametric regression estimation under anisotropic Hölder condition ⋮ Adaptive learning rates for support vector machines working on data with low intrinsic dimension

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Noise-robust edge detector combining isotropic and anisotropic Gaussian kernels
• Spline smoothing in regression models and asymptotic efficiency in \(L_ 2\)
• An SVM-like approach for expectile regression
• Optimal global rates of convergence for nonparametric regression
• Random rates in anisotropic regression. (With discussion)
• Optimal regression rates for SVMs using Gaussian kernels
• On estimating a density using Hellinger distance and some other strange facts
• Anisotropic function estimation using multi-bandwidth Gaussian processes
• Learning Deep Architectures for AI
• Learning Theory
• Support Vector Machines
• Anisotropic Spaces I. (Interpolation of Abstract Spaces and Function Spaces)

This page was built for publication: Optimal learning with anisotropic Gaussian SVMs