Regularization in kernel learning

DOI10.1214/09-AOS728zbMath1191.68356arXiv1001.2094MaRDI QIDQ847647

Joseph Neeman, Shahar Mendelson

Publication date: 19 February 2010

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

Full work available at URL: https://arxiv.org/abs/1001.2094

zbMATH Keywords

regulationmodel selectionleast-squaresregressionreproducing kernel Hilbert space

Mathematics Subject Classification ID

Computational learning theory (68Q32) Stochastic processes (60G99)

Related Items (42)

Efficient kernel-based variable selection with sparsistency ⋮ Ivanov-Regularised Least-Squares Estimators over Large RKHSs and Their Interpolation Spaces ⋮ Least-squares regularized regression with dependent samples andq-penalty ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Integral operator approach to learning theory with unbounded sampling ⋮ Learning with coefficient-based regularization and \(\ell^1\)-penalty ⋮ \(\ell _{1}\)-regularized linear regression: persistence and oracle inequalities ⋮ Optimal learning rates for least squares regularized regression with unbounded sampling ⋮ Convex regularization in statistical inverse learning problems ⋮ Orthogonal statistical learning ⋮ Measuring Complexity of Learning Schemes Using Hessian-Schatten Total Variation ⋮ Structure learning via unstructured kernel-based M-estimation ⋮ Concentration estimates for learning with unbounded sampling ⋮ Mercer's theorem on general domains: on the interaction between measures, kernels, and RKHSs ⋮ Consistency of support vector machines using additive kernels for additive models ⋮ Estimating conditional quantiles with the help of the pinball loss ⋮ Optimal regression rates for SVMs using Gaussian kernels ⋮ ERM and RERM are optimal estimators for regression problems when malicious outliers corrupt the labels ⋮ General nonexact oracle inequalities for classes with a subexponential envelope ⋮ Fast learning from \(\alpha\)-mixing observations ⋮ Learning with Convex Loss and Indefinite Kernels ⋮ Learning Theory Estimates with Observations from General Stationary Stochastic Processes ⋮ Optimal rates for regularization of statistical inverse learning problems ⋮ Learning rates for kernel-based expectile regression ⋮ Kernel variable selection for multicategory support vector machines ⋮ A short note on the comparison of interpolation widths, entropy numbers, and Kolmogorov widths ⋮ Learning Rates of l^q Coefficient Regularization Learning with Gaussian Kernel ⋮ Coefficient-based regression with non-identical unbounded sampling ⋮ Distributed regularized least squares with flexible Gaussian kernels ⋮ Generalized support vector regression: Duality and tensor-kernel representation ⋮ Convergence Rates of Spectral Regularization Methods: A Comparison between Ill-Posed Inverse Problems and Statistical Kernel Learning ⋮ Fast and strong convergence of online learning algorithms ⋮ Asymptotic normality of support vector machine variants and other regularized kernel methods ⋮ Multikernel Regression with Sparsity Constraint ⋮ Unnamed Item ⋮ On the speed of uniform convergence in Mercer's theorem ⋮ Optimal learning with Gaussians and correntropy loss ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Thresholded spectral algorithms for sparse approximations

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Regularity of Gaussian processes
• Some limit theorems for empirical processes (with discussion)
• \(L_{p}\)-moments of random vectors via majorizing measures
• Concentration inequalities and model selection. Ecole d'Eté de Probabilités de Saint-Flour XXXIII -- 2003.
• Subspaces and orthogonal decompositions generated by bounded orthogonal systems
• Obtaining fast error rates in nonconvex situations
• Fast rates for support vector machines using Gaussian kernels
• Random vectors in the isotropic position
• Sharper bounds for Gaussian and empirical processes
• Best choices for regularization parameters in learning theory: on the bias-variance problem.
• About the constants in Talagrand's concentration inequalities for empirical processes.
• The covering number in learning theory
• \(\ell _{1}\)-regularized linear regression: persistence and oracle inequalities
• Local Rademacher complexities and oracle inequalities in risk minimization. (2004 IMS Medallion Lecture). (With discussions and rejoinder)
• Optimal rates for the regularized least-squares algorithm
• Statistical performance of support vector machines
• On weakly bounded empirical processes
• Reconstruction and subgaussian operators in asymptotic geometric analysis
• Empirical minimization
• Learning rates of least-square regularized regression
• Local Rademacher complexities
• Learning theory estimates via integral operators and their approximations
• On the mathematical foundations of learning
• Learning Theory
• FAST RATES FOR ESTIMATION ERROR AND ORACLE INEQUALITIES FOR MODEL SELECTION
• ESTIMATES OF SINGULAR NUMBERS OF INTEGRAL OPERATORS
• Uniform Central Limit Theorems
• ESTIMATING THE APPROXIMATION ERROR IN LEARNING THEORY
• Generalization performance of regularization networks and support vector machines via entropy numbers of compact operators
• The Generic Chaining
• The importance of convexity in learning with squared loss
• 10.1162/1532443041424337

This page was built for publication: Regularization in kernel learning