Adaptive kernel methods using the balancing principle

DOI10.1007/s10208-010-9064-2zbMath1204.68154OpenAlexW2139252659MaRDI QIDQ1959089

Ernesto De Vito, Lorenzo Rosasco, Sergei V. Pereverzyev

Publication date: 6 October 2010

Published in: Foundations of Computational Mathematics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10208-010-9064-2

zbMATH Keywords

adaptive Regularizationinverse Problemslearning Theorymodel Selection

Mathematics Subject Classification ID

Computational learning theory (68Q32) Learning and adaptive systems in artificial intelligence (68T05)

Related Items

Concentration inequalities for cross-validation in scattered data approximation ⋮ Multi-penalty regularization in learning theory ⋮ Optimal learning rates for kernel partial least squares ⋮ Optimal Convergence of the Discrepancy Principle for Polynomially and Exponentially Ill-Posed Operators under White Noise ⋮ A machine learning approach to optimal Tikhonov regularization I: Affine manifolds ⋮ On an unsupervised method for parameter selection for the elastic net ⋮ Gradient descent for robust kernel-based regression ⋮ A linear functional strategy for regularized ranking ⋮ Manifold regularization based on Nyström type subsampling ⋮ Multi-task learning via linear functional strategy ⋮ A Lepskiĭ-type stopping rule for the covariance estimation of multi-dimensional Lévy processes ⋮ On the K-functional in learning theory ⋮ Unnamed Item ⋮ A meta-learning approach to the regularized learning -- case study: blood glucose prediction ⋮ A Study on Regularization for Discrete Inverse Problems with Model-Dependent Noise ⋮ Kernel gradient descent algorithm for information theoretic learning ⋮ Distributed learning and distribution regression of coefficient regularization ⋮ The Goldenshluger-Lepski method for constrained least-squares estimators over RKHSs ⋮ Robust kernel-based distribution regression ⋮ Multi-parameter regularization and its numerical realization ⋮ Balancing principle in supervised learning for a general regularization scheme ⋮ Regularized Nyström subsampling in regression and ranking problems under general smoothness assumptions ⋮ About the Balancing Principle for Choice of the Regularization Parameter ⋮ On a regularization of unsupervised domain adaptation in RKHS ⋮ Fast cross-validation in harmonic approximation ⋮ Unnamed Item ⋮ Error analysis of the kernel regularized regression based on refined convex losses and RKBSs

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Asymptotics of cross-validated risk estimation in estimator selection and performance assess\-ment
• On regularization algorithms in learning theory
• Elastic-net regularization in learning theory
• Risk bounds for model selection via penalization
• On adaptive inverse estimation of linear functional in Hilbert scales
• Complexity regularization via localized random penalties
• Optimal aggregation of classifiers in statistical learning.
• Regularization networks and support vector machines
• 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
• Approximation methods for supervised learning
• Consistency and robustness of kernel-based regression in convex risk minimization
• Learning rates of least-square regularized regression
• Learning theory estimates via integral operators and their approximations
• On early stopping in gradient descent learning
• On the mathematical foundations of learning
• Regularization Algorithms for Learning That Are Equivalent to Multilayer Networks
• Theory of Classification: a Survey of Some Recent Advances
• Learning Theory
• Oracle inequalities for multi-fold cross validation
• CROSS-VALIDATION BASED ADAPTATION FOR REGULARIZATION OPERATORS IN LEARNING THEORY
• Boosting With theL₂Loss
• On a Problem of Adaptive Estimation in Gaussian White Noise
• Regularization and Variable Selection Via the Elastic Net
• On the Adaptive Selection of the Parameter in Regularization of Ill-Posed Problems
• The Lepskii principle revisited
• Theory of Reproducing Kernels
• Introduction to nonparametric estimation
• The elements of statistical learning. Data mining, inference, and prediction