Learning theory estimates via integral operators and their approximations

DOI10.1007/S00365-006-0659-YzbMath1127.68088OpenAlexW1970781863WikidataQ56169176 ScholiaQ56169176MaRDI QIDQ2642918

Ding-Xuan Zhou, Stephen Smale

Publication date: 6 September 2007

Published in: Constructive Approximation (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s00365-006-0659-y

zbMATH Keywords

classification problem

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05) Fourier and Fourier-Stieltjes transforms and other transforms of Fourier type (42B10) Hilbert spaces with reproducing kernels (= (proper) functional Hilbert spaces, including de Branges-Rovnyak and other structured spaces) (46E22) Sampling theory in information and communication theory (94A20)

Related Items (only showing first 100 items - show all)

Machine learning with kernels for portfolio valuation and risk management ⋮ Online regression with unbounded sampling ⋮ Coefficient regularized regression with non-iid sampling ⋮ Efficient kernel-based variable selection with sparsistency ⋮ Normal estimation on manifolds by gradient learning ⋮ LOCAL LEARNING ESTIMATES BY INTEGRAL OPERATORS ⋮ Reproducing properties of differentiable Mercer-like kernels ⋮ LEAST SQUARE REGRESSION WITH COEFFICIENT REGULARIZATION BY GRADIENT DESCENT ⋮ Complexity control in statistical learning ⋮ Symmetric Measures, Continuous Networks, and Dynamics ⋮ Consistent identification of Wiener systems: a machine learning viewpoint ⋮ Learning by atomic norm regularization with polynomial kernels ⋮ The kernel regularized learning algorithm for solving Laplace equation with Dirichlet boundary ⋮ Least-squares regularized regression with dependent samples andq-penalty ⋮ ERM learning algorithm for multi-class classification ⋮ Fully online classification by regularization ⋮ Distributed spectral pairwise ranking algorithms ⋮ THE COEFFICIENT REGULARIZED REGRESSION WITH RANDOM PROJECTION ⋮ Online regularized pairwise learning with non-i.i.d. observations ⋮ Optimal Quadrature-Sparsification for Integral Operator Approximation ⋮ Learning with sample dependent hypothesis spaces ⋮ Application of integral operator for regularized least-square regression ⋮ Nonlinear predictive directions in clinical trials ⋮ A Bayesian approach to sparse dynamic network identification ⋮ Learning rates of kernel-based robust classification ⋮ The optimal solution of multi-kernel regularization learning ⋮ Von Neumann indices and classes of positive definite functions ⋮ The consistency of least-square regularized regression with negative association sequence ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Unnamed Item ⋮ ℓ¹-Norm support vector machine for ranking with exponentially strongly mixing sequence ⋮ Gradient descent for robust kernel-based regression ⋮ Reproducing kernels: harmonic analysis and some of their applications ⋮ Deterministic error bounds for kernel-based learning techniques under bounded noise ⋮ Asymptotic expansions and Voronovskaja type theorems for the multivariate neural network operators ⋮ Distributed learning with multi-penalty regularization ⋮ Decomposition of Gaussian processes, and factorization of positive definite kernels ⋮ Exact asymptotic orders of various randomized widths on Besov classes ⋮ Learning rates for the kernel regularized regression with a differentiable strongly convex loss ⋮ Quantitative convergence analysis of kernel based large-margin unified machines ⋮ Kernel-based maximum correntropy criterion with gradient descent method ⋮ The convergence rate of semi-supervised regression with quadratic loss ⋮ Approximation of Lyapunov functions from noisy data ⋮ On the K-functional in learning theory ⋮ Unnamed Item ⋮ Regression learning with non-identically and non-independently sampling ⋮ Learning rates of regularized regression for exponentially strongly mixing sequence ⋮ Spectral Algorithms for Supervised Learning ⋮ Nonasymptotic analysis of robust regression with modified Huber's loss ⋮ ERM and RERM are optimal estimators for regression problems when malicious outliers corrupt the labels ⋮ Bias corrected regularization kernel method in ranking ⋮ The performance of semi-supervised Laplacian regularized regression with the least square loss ⋮ Stability and optimization error of stochastic gradient descent for pairwise learning ⋮ Distributed learning and distribution regression of coefficient regularization ⋮ Coefficient-based regularization network with variance loss for error ⋮ Reproducing kernels and choices of associated feature spaces, in the form of \(L^2\)-spaces ⋮ Kernel variable selection for multicategory support vector machines ⋮ Sharp estimates for eigenvalues of integral operators generated by dot product kernels on the sphere ⋮ Robust kernel-based distribution regression ⋮ REGULARIZED LEAST SQUARE ALGORITHM WITH TWO KERNELS ⋮ Convergence rates of learning algorithms by random projection ⋮ Learning gradients by a gradient descent algorithm ⋮ On empirical eigenfunction-based ranking with \(\ell^1\) norm regularization ⋮ Least-square regularized regression with non-iid sampling ⋮ Application of integral operator for vector-valued regression learning ⋮ Balancing principle in supervised learning for a general regularization scheme ⋮ Simultaneous estimations of optimal directions and optimal transformations for functional data ⋮ Optimal learning rates for distribution regression ⋮ Least Square Regression with l^p-Coefficient Regularization ⋮ Approximating and learning by Lipschitz kernel on the sphere ⋮ Error analysis of multicategory support vector machine classifiers ⋮ ONLINE LEARNING WITH MARKOV SAMPLING ⋮ The information-based complexity of approximation problem by adaptive Monte Carlo methods ⋮ Learning rates of gradient descent algorithm for classification ⋮ Probabilistic error bounds on constraint violation for empirical-analytical Lagrangian models of motion ⋮ Optimal rates for spectral algorithms with least-squares regression over Hilbert spaces ⋮ Regularized Nyström subsampling in regression and ranking problems under general smoothness assumptions ⋮ Moving quantile regression ⋮ 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 ⋮ Gradient-Based Kernel Dimension Reduction for Regression ⋮ SVM LEARNING AND L^p APPROXIMATION BY GAUSSIANS ON RIEMANNIAN MANIFOLDS ⋮ A NOTE ON STABILITY OF ERROR BOUNDS IN STATISTICAL LEARNING THEORY ⋮ Regularized ranking with convex losses and \(\ell^1\)-penalty ⋮ Reproducing Kernel Banach Spaces with the ℓ¹ Norm II: Error Analysis for Regularized Least Square Regression ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Optimal rates for coefficient-based regularized regression ⋮ Boosting as a kernel-based method ⋮ INDEFINITE KERNEL NETWORK WITH DEPENDENT SAMPLING ⋮ Half supervised coefficient regularization for regression learning with unbounded sampling ⋮ Unnamed Item ⋮ Functional linear regression with Huber loss ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Error analysis of the kernel regularized regression based on refined convex losses and RKBSs ⋮ CONVERGENCE ANALYSIS OF COEFFICIENT-BASED REGULARIZATION UNDER MOMENT INCREMENTAL CONDITION ⋮ Regularization: From Inverse Problems to Large-Scale Machine Learning

This page was built for publication: Learning theory estimates via integral operators and their approximations