Least square regression with indefinite kernels and coefficient regularization

DOI10.1016/j.acha.2010.04.001zbMath1225.65015OpenAlexW2045386260MaRDI QIDQ617706

Hongwei Sun, Qiang Wu

Publication date: 13 January 2011

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

Full work available at URL: https://doi.org/10.1016/j.acha.2010.04.001

zbMATH Keywords

convergencenumerical examplesintegral operatorregression functionreproducing kernel Hilbert spaceGaussian kernelMercer kernelindefinite kernelcapacity independent error boundscoefficient regularizationleast square regressionlearning rates

Mathematics Subject Classification ID

Related Items (45)

Coefficient regularized regression with non-iid sampling ⋮ Statistical consistency of coefficient-based conditional quantile regression ⋮ Distributed regression learning with coefficient regularization ⋮ Indefinite kernels in least squares support vector machines and principal component analysis ⋮ Distributed learning with partial coefficients regularization ⋮ Learning rate of distribution regression with dependent samples ⋮ Error Analysis of Coefficient-Based Regularized Algorithm for Density-Level Detection ⋮ Regularized least square regression with unbounded and dependent sampling ⋮ Sharp learning rates of coefficient-based \(l^q\)-regularized regression with indefinite kernels ⋮ Kernel-based sparse regression with the correntropy-induced loss ⋮ The learning rate of \(l_2\)-coefficient regularized classification with strong loss ⋮ Distributed semi-supervised regression learning with coefficient regularization ⋮ Learning rates for least square regressions with coefficient regularization ⋮ Least squares regression with \(l_1\)-regularizer in sum space ⋮ On the K-functional in learning theory ⋮ An empirical feature-based learning algorithm producing sparse approximations ⋮ Regression learning with non-identically and non-independently sampling ⋮ Learning rates of multitask kernel methods ⋮ Learning from regularized regression algorithms with \(p\)-order Markov chain sampling ⋮ Coefficient-based regularized distribution regression ⋮ Consistency analysis of spectral regularization algorithms ⋮ Conditional quantiles with varying Gaussians ⋮ Learning with Convex Loss and Indefinite Kernels ⋮ Convergence rate of the semi-supervised greedy algorithm ⋮ Kernelized Elastic Net Regularization: Generalization Bounds, and Sparse Recovery ⋮ Unified approach to coefficient-based regularized regression ⋮ A simpler approach to coefficient regularized support vector machines regression ⋮ Indefinite kernel network with \(l^q\)-norm regularization ⋮ Distributed learning and distribution regression of coefficient regularization ⋮ Convergence rate of kernel canonical correlation analysis ⋮ Constructive analysis for coefficient regularization regression algorithms ⋮ Coefficient-based regularization network with variance loss for error ⋮ Support vector machines regression with \(l^1\)-regularizer ⋮ Learning Rates of l^q Coefficient Regularization Learning with Gaussian Kernel ⋮ Coefficient-based regression with non-identical unbounded sampling ⋮ Coefficient-based \(l^q\)-regularized regression with indefinite kernels and unbounded sampling ⋮ Regularized modal regression with data-dependent hypothesis spaces ⋮ Nyström subsampling method for coefficient-based regularized regression ⋮ Distributed learning with indefinite kernels ⋮ Reproducing Kernel Banach Spaces with the ℓ¹ Norm II: Error Analysis for Regularized Least Square Regression ⋮ Optimal rates for coefficient-based regularized regression ⋮ INDEFINITE KERNEL NETWORK WITH DEPENDENT SAMPLING ⋮ Half supervised coefficient regularization for regression learning with unbounded sampling ⋮ Supervised learning with indefinite topological Kernels ⋮ CONVERGENCE ANALYSIS OF COEFFICIENT-BASED REGULARIZATION UNDER MOMENT INCREMENTAL CONDITION

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Learning by nonsymmetric kernels with data dependent spaces and \(\ell^1\)-regularizer
• Regularized least square regression with dependent samples
• On regularization algorithms in learning theory
• Multi-kernel regularized classifiers
• A note on application of integral operator in learning theory
• Support vector machine classification with indefinite kernels
• Best choices for regularization parameters in learning theory: on the bias-variance problem.
• Regularization networks and support vector machines
• Learning with sample dependent hypothesis spaces
• Application of integral operator for regularized least-square regression
• Learning rates of least-square regularized regression
• Shannon sampling. II: Connections to learning theory
• Learning theory estimates via integral operators and their approximations
• On the mathematical foundations of learning
• Spectral Algorithms for Supervised Learning
• SVM Soft Margin Classifiers: Linear Programming versus Quadratic Programming
• 10.1162/153244302760200650
• Shannon sampling and function reconstruction from point values
• Leave-One-Out Bounds for Kernel Methods
• Learning Bounds for Kernel Regression Using Effective Data Dimensionality
• Theory of Reproducing Kernels

This page was built for publication: Least square regression with indefinite kernels and coefficient regularization