Adaptive learning rates for support vector machines working on data with low intrinsic dimension

DOI10.1214/21-AOS2078zbMath1486.62107arXiv2003.06202OpenAlexW3010957709MaRDI QIDQ2073699

Thomas Hamm, Ingo Steinwart

Publication date: 7 February 2022

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2003.06202

zbMATH Keywords

classificationcurse of dimensionalityregressionsupport vector machineslearning rates

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05)

Related Items (1)

Intrinsic Dimension Adaptive Partitioning for Kernel Methods

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Bayesian manifold regression
• A tree-based regressor that adapts to intrinsic dimension
• Covering numbers of Gaussian reproducing kernel Hilbert spaces
• Estimating conditional quantiles with the help of the pinball loss
• Learning rates for kernel-based expectile regression
• Adaptive Bayesian estimation using a Gaussian random field with inverse gamma bandwidth
• Learning and approximation by Gaussians on Riemannian manifolds
• Theory of function spaces II
• Fast rates for support vector machines using Gaussian kernels
• Fast learning rates for plug-in classifiers
• On the concept of attractor
• Strange attractors
• The analysis of linear partial differential operators. I: Distribution theory and Fourier analysis.
• Smooth discrimination analysis
• Improved classification rates under refined margin conditions
• Über einige Kreisüberdeckungen
• Optimal global rates of convergence for nonparametric regression
• A distribution-free theory of nonparametric regression
• New approaches to statistical learning theory
• Optimal aggregation of classifiers in statistical learning.
• Optimal regression rates for SVMs using Gaussian kernels
• Optimal learning with anisotropic Gaussian SVMs
• SVM LEARNING AND L^p APPROXIMATION BY GAUSSIANS ON RIEMANNIAN MANIFOLDS
• Support Vector Machines
• Minimax-optimal classification with dyadic decision trees
• Rates of convergence of nearest neighbor estimation under arbitrary sampling

This page was built for publication: Adaptive learning rates for support vector machines working on data with low intrinsic dimension