Sharp learning rates of coefficient-based \(l^q\)-regularized regression with indefinite kernels

DOI10.1007/s11425-013-4688-8zbMath1272.68343OpenAlexW2272469130MaRDI QIDQ370936

Daimin Shi, Mingshan Zhang, Quan-Wu Xiao, Shao-Gao Lv

Publication date: 20 September 2013

Published in: Science China. Mathematics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s11425-013-4688-8

zbMATH Keywords

learning theoryreproducing kernel Hilbert spacescovering numbercoefficient-based regularizationindefinite kernel

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Computational learning theory (68Q32) Learning and adaptive systems in artificial intelligence (68T05)

Related Items (6)

Error analysis for \(l^q\)-coefficient regularized moving least-square regression ⋮ Distributed learning with partial coefficients regularization ⋮ Distributed semi-supervised regression learning with coefficient regularization ⋮ Constructive analysis for least squares regression with generalized \(K\)-norm regularization ⋮ Constructive analysis for coefficient regularization regression algorithms ⋮ Coefficient-based \(l^q\)-regularized regression with indefinite kernels and unbounded sampling

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A kernel-based framework to tensorial data analysis
• Learning by nonsymmetric kernels with data dependent spaces and \(\ell^1\)-regularizer
• Concentration estimates for learning with \(\ell ^{1}\)-regularizer and data dependent hypothesis spaces
• Least square regression with indefinite kernels and coefficient regularization
• Unified approach to coefficient-based regularized regression
• On regularization algorithms in learning theory
• Best choices for regularization parameters in learning theory: on the bias-variance problem.
• Optimum bounds for the distributions of martingales in Banach spaces
• Weak convergence and empirical processes. With applications to statistics
• A kernel-based perceptron with dynamic memory
• An approximation theory approach to learning with \(\ell^1\) regularization
• Regularization networks and support vector machines
• Learning with sample dependent hypothesis spaces
• Multiscale kernels
• Learning theory estimates via integral operators and their approximations
• On the mathematical foundations of learning
• Learning Theory
• ONLINE LEARNING WITH MARKOV SAMPLING
• 10.1162/153244302760200704
• Leave-One-Out Bounds for Kernel Methods
• 10.1162/1532443041424337

This page was built for publication: Sharp learning rates of coefficient-based \(l^q\)-regularized regression with indefinite kernels