Optimal learning rates for localized SVMs

MaRDI QIDQ2953612zbMATH OpenFDO

Authors Mona Meister, Ingo Steinwart

Publication date 5 January 2017

Full work available at URL https://arxiv.org/abs/1507.06615, http://jmlr.csail.mit.edu/papers/v17/14-023.html

zbMATH Keywords

least squares regressionlocalizationsupport vector machines

Mathematics Subject Classification ID

Inequalities; stochastic orderings (60E15) Nonparametric regression and quantile regression (62G08) Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Improved classification rates for localized algorithms under margin conditions
• Adaptive rates for support vector machines
• Fast and scalable local kernel machines
• Quantitative robustness of localized support vector machines
• Optimal regression rates for SVMs using Gaussian kernels

Cited in

(11)

• Quantitative robustness of localized support vector machines
• Distributed learning with regularized least squares
• Improved classification rates for localized algorithms under margin conditions
• Histogram transform ensembles for large-scale regression
• Intrinsic dimension adaptive partitioning for kernel methods
• scientific article; zbMATH DE number 7568237 (Why is no real title available?)
• scientific article; zbMATH DE number 7306853 (Why is no real title available?)
• Hybrid learning based on Fisher linear discriminant
• Adaptive parameter selection for kernel ridge regression
• Learning rates for kernel-based expectile regression
• Kernel Spectral Joint Embeddings for High-Dimensional Noisy Datasets Using Duo-Landmark Integral Operators

This page was built for publication: Optimal learning rates for localized SVMs

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2953612)