Learning rates for the kernel regularized regression with a differentiable strongly convex loss

DOI10.3934/cpaa.2020176zbMath1445.68193MaRDI QIDQ2191832

Huanxiang Liu, Hui-min Wang, Bao Huai Sheng

Publication date: 26 June 2020

Published in: Communications on Pure and Applied Analysis (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.3934/cpaa.2020176

zbMATH Keywords

\(K\)-functional; learning rate; reproducing-kernel Hilbert space; Hutchinson metric; conjugate loss; differentiable strongly convex loss; kernel-regularized regression; maximum mean discrepancy (MMD)

Mathematics Subject Classification ID

62J02: General nonlinear regression

90C25: Convex programming

68T05: Learning and adaptive systems in artificial intelligence

46E22: Hilbert spaces with reproducing kernels (= (proper) functional Hilbert spaces, including de Branges-Rovnyak and other structured spaces)

Related Items

Error analysis of the kernel regularized regression based on refined convex losses and RKBSs, Convergence analysis for kernel-regularized online regression associated with an RRKHS, Error analysis of kernel regularized pairwise learning with a strongly convex loss, Learning rates of kernel-based robust classification

Uses Software

• ElemStatLearn
• ckn_kernel

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• On the robustness of regularized pairwise learning methods based on kernels
• ERM scheme for quantile regression
• The learning rate of \(l_2\)-coefficient regularized classification with strong loss
• Editorial: On the interface of statistics and machine learning
• On qualitative robustness of support vector machines
• Optimal learning rates for least squares regularized regression with unbounded sampling
• Estimating conditional quantiles with the help of the pinball loss
• Optimal rates for regularization of statistical inverse learning problems
• Learning rates for kernel-based expectile regression
• Model selection for regularized least-squares algorithm in learning theory
• On regularization algorithms in learning theory
• A way of construction spherical zonal translation network operators with linear bounded operators
• The convergence rate for a \(K\)-functional in learning theory
• Analysis of support vector machines regression
• Robustness of reweighted least squares kernel based regression
• epsilon-entropy of convex sets and functions
• Error analysis on Hérmite learning with gradient data
• Best choices for regularization parameters in learning theory: on the bias-variance problem.
• Statistical behavior and consistency of classification methods based on convex risk minimization.
• Learning rates for least square regressions with coefficient regularization
• ERM learning with unbounded sampling
• Optimal regression rates for SVMs using Gaussian kernels
• Conditional quantiles with varying Gaussians
• Regularization networks and support vector machines
• Learning sets with separating kernels
• Universality of deep convolutional neural networks
• Optimal rates for spectral algorithms with least-squares regression over Hilbert spaces
• Optimal rates for the regularized least-squares algorithm
• Application of integral operator for regularized least-square regression
• The convergence rate of semi-supervised regression with quadratic loss
• On approximation by reproducing kernel spaces in weighted \(L^p\) spaces
• A review on consistency and robustness properties of support vector machines for heavy-tailed distributions
• Consistency and robustness of kernel-based regression in convex risk minimization
• Approximation with polynomial kernels and SVM classifiers
• Learning rates of least-square regularized regression
• On approximation by spherical zonal translation networks based on Bochner-Riesz means
• Learning theory estimates via integral operators and their approximations
• On the mathematical foundations of learning
• Application of integral operator for vector-valued regression learning
• Learning rates for the risk of kernel-based quantile regression estimators in additive models
• Convergence rates of Kernel Conjugate Gradient for random design regression
• CONVERGENCE ANALYSIS OF COEFFICIENT-BASED REGULARIZATION UNDER MOMENT INCREMENTAL CONDITION
• Hilbert space embeddings and metrics on probability measures
• Convex Optimization in Normed Spaces
• Covering Numbers for Convex Functions
• GENERALIZATION BOUNDS OF REGULARIZATION ALGORITHMS DERIVED SIMULTANEOUSLY THROUGH HYPOTHESIS SPACE COMPLEXITY, ALGORITHMIC STABILITY AND DATA QUALITY
• Support Vector Machines
• Capacity of reproducing kernel spaces in learning theory
• Consistency of kernel-based quantile regression
• ESTIMATING THE APPROXIMATION ERROR IN LEARNING THEORY
• Deep distributed convolutional neural networks: Universality
• Gradient descent for robust kernel-based regression
• Kernel Mean Embedding of Distributions: A Review and Beyond
• Convergence rate of SVM for kernel-based robust regression
• 10.1162/1532443041827925
• Fast learning rates for regularized regression algorithms
• On the K-functional in learning theory
• A representer theorem for deep kernel learning
• Convexity, Classification, and Risk Bounds
• Theory of Reproducing Kernels
• Convex analysis and monotone operator theory in Hilbert spaces
• The elements of statistical learning. Data mining, inference, and prediction