Learning Theory

DOI10.1017/CBO9780511618796zbMath1274.41001OpenAlexW4245558064MaRDI QIDQ3426914

Ding-Xuan Zhou, Felipe Cucker

Publication date: 13 March 2007

Full work available at URL: https://doi.org/10.1017/cbo9780511618796

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Computational learning theory (68Q32) Learning and adaptive systems in artificial intelligence (68T05) System identification (93B30) Research exposition (monographs, survey articles) pertaining to statistics (62-02) Stochastic learning and adaptive control (93E35) Abstract approximation theory (approximation in normed linear spaces and other abstract spaces) (41A65) Spline approximation (41A15) Research exposition (monographs, survey articles) pertaining to computer science (68-02) Research exposition (monographs, survey articles) pertaining to approximations and expansions (41-02)

Related Items

Machine learning with kernels for portfolio valuation and risk management ⋮ Online gradient descent algorithms for functional data learning ⋮ Discrete least-squares approximations over optimized downward closed polynomial spaces in arbitrary dimension ⋮ Learning performance of regularized moving least square regression ⋮ Stable splittings of Hilbert spaces of functions of infinitely many variables ⋮ Online regularized learning with pairwise loss functions ⋮ Online regression with unbounded sampling ⋮ Multivariate weighted Kantorovich operators ⋮ Operator-theoretic framework for forecasting nonlinear time series with kernel analog techniques ⋮ Normal estimation on manifolds by gradient learning ⋮ Binary separation and training support vector machines ⋮ Approximations of conditional probability density functions in Lebesgue spaces via mixture of experts models ⋮ On Gaussian kernels on Hilbert spaces and kernels on hyperbolic spaces ⋮ Least-squares regularized regression with dependent samples andq-penalty ⋮ ERM learning algorithm for multi-class classification ⋮ On grouping effect of elastic net ⋮ THE COEFFICIENT REGULARIZED REGRESSION WITH RANDOM PROJECTION ⋮ Divergence-free quasi-interpolation ⋮ Error bounds of multi-graph regularized semi-supervised classification ⋮ Learning interaction kernels in stochastic systems of interacting particles from multiple trajectories ⋮ ℓ¹-Norm support vector machine for ranking with exponentially strongly mixing sequence ⋮ Fast rates of minimum error entropy with heavy-tailed noise ⋮ Learning rate of distribution regression with dependent samples ⋮ Distributed kernel gradient descent algorithm for minimum error entropy principle ⋮ Kernel-based sparse regression with the correntropy-induced loss ⋮ A new randomized Kaczmarz based kernel canonical correlation analysis algorithm with applications to information retrieval ⋮ Distributed semi-supervised regression learning with coefficient regularization ⋮ Echo state networks are universal ⋮ Distributed learning with multi-penalty regularization ⋮ On reproducing kernel Banach spaces: generic definitions and unified framework of constructions ⋮ Multivariate integration for analytic functions with Gaussian kernels ⋮ Deep CNNs as universal predictors of elasticity tensors in homogenization ⋮ Kolmogorov widths on the sphere via eigenvalue estimates for Hölderian integral operators ⋮ On the universal transformation of data-driven models to control systems ⋮ The convergence rate of semi-supervised regression with quadratic loss ⋮ Tractability of Function Approximation with Product Kernels ⋮ Topology, convergence, and reconstruction of predictive states ⋮ Regression learning with non-identically and non-independently sampling ⋮ Random sampling in reproducing kernel subspaces of \(L^p(\mathbb{R}^n)\) ⋮ Optimal classification of Gaussian processes in homo- and heteroscedastic settings ⋮ Local RBF-based penalized least-squares approximation on the sphere with noisy scattered data ⋮ Partial multi-dividing ontology learning algorithm ⋮ Convergence analysis of online learning algorithm with two-stage step size ⋮ The performance of semi-supervised Laplacian regularized regression with the least square loss ⋮ Fast learning from \(\alpha\)-mixing observations ⋮ Convolution random sampling in multiply generated shift-invariant spaces of \(L^p(\mathbb{R}^d)\) ⋮ Random sampling in multiply generated shift-invariant subspaces of mixed Lebesgue spaces \(L^{p,q}(\mathbb{R}\times\mathbb{R}^d)\) ⋮ Kernel conjugate gradient methods with random projections ⋮ Optimal learning with anisotropic Gaussian SVMs ⋮ Reproducing kernels and choices of associated feature spaces, in the form of \(L^2\)-spaces ⋮ Learning performance of regularized regression with multiscale kernels based on Markov observations ⋮ A closer look at covering number bounds for Gaussian kernels ⋮ Multi-task learning in vector-valued reproducing kernel Banach spaces with the \(\ell^1\) norm ⋮ Convergence rates of learning algorithms by random projection ⋮ On empirical eigenfunction-based ranking with \(\ell^1\) norm regularization ⋮ Coefficient-based regression with non-identical unbounded sampling ⋮ Mathematics of the neural response ⋮ Asymptotic expansion for neural network operators of the Kantorovich type and high order of approximation ⋮ Rademacher Chaos Complexities for Learning the Kernel Problem ⋮ Optimal learning rates for distribution regression ⋮ Learning rate of magnitude-preserving regularization ranking with dependent samples ⋮ Error analysis of multicategory support vector machine classifiers ⋮ Some new bounds on the entropy numbers of diagonal operators ⋮ Convergence analysis of deterministic kernel-based quadrature rules in misspecified settings ⋮ Learning rates for the risk of kernel-based quantile regression estimators in additive models ⋮ Online pairwise learning algorithms with convex loss functions ⋮ Numerical solution of the parametric diffusion equation by deep neural networks ⋮ Learning with correntropy-induced losses for regression with mixture of symmetric stable noise ⋮ Optimal rates for spectral algorithms with least-squares regression over Hilbert spaces ⋮ Old and New on the Laplace-Beltrami Derivative ⋮ Moving quantile regression ⋮ Analysis of regularized least-squares in reproducing kernel Kreĭn spaces ⋮ A promenade through correct test sequences. I: Degree of constructible sets, Bézout's inequality and density ⋮ A statistical learning assessment of Huber regression ⋮ GENERALIZATION BOUNDS OF REGULARIZATION ALGORITHMS DERIVED SIMULTANEOUSLY THROUGH HYPOTHESIS SPACE COMPLEXITY, ALGORITHMIC STABILITY AND DATA QUALITY ⋮ Variational Monte Carlo -- bridging concepts of machine learning and high-dimensional partial differential equations ⋮ Fast and strong convergence of online learning algorithms ⋮ A direct approach for function approximation on data defined manifolds ⋮ Optimal stochastic Bernstein polynomials in Ditzian-Totik type modulus of smoothness ⋮ \(L_2\)-norm sampling discretization and recovery of functions from RKHS with finite trace ⋮ Universalities of reproducing kernels revisited ⋮ Random sampling and approximation of signals with bounded derivatives ⋮ Superquantiles at work: machine learning applications and efficient subgradient computation ⋮ The learning rates of regularized regression based on reproducing kernel Banach spaces ⋮ Regularized ranking with convex losses and \(\ell^1\)-penalty ⋮ On extension theorems and their connection to universal consistency in machine learning ⋮ Error bounds for learning the kernel ⋮ Generalized Dobrushin ergodicity coefficient and ergodicities of non-homogeneous Markov chains ⋮ A statistical learning perspective on switched linear system identification ⋮ Interpolation, the rudimentary geometry of spaces of Lipschitz functions, and geometric complexity ⋮ Optimal rates for coefficient-based regularized regression ⋮ On the speed of uniform convergence in Mercer's theorem ⋮ INDEFINITE KERNEL NETWORK WITH DEPENDENT SAMPLING ⋮ Stochastic quasi-interpolation with Bernstein polynomials ⋮ Extreme learning machine for ranking: generalization analysis and applications ⋮ Sharp estimates for the covering numbers of the Weierstrass fractal kernel ⋮ Functional linear regression with Huber loss ⋮ ERROR ANALYSIS FOR THE SPARSE GRAPH-BASED SEMI-SUPERVISED CLASSIFICATION ALGORITHM ⋮ KERNEL METHODS FOR INDEPENDENCE MEASUREMENT WITH COEFFICIENT CONSTRAINTS ⋮ CONVERGENCE ANALYSIS OF COEFFICIENT-BASED REGULARIZATION UNDER MOMENT INCREMENTAL CONDITION ⋮ Stochastic subspace correction in Hilbert space ⋮ Optimal sampling points in reproducing kernel Hilbert spaces ⋮ Convergence rate for the moving least-squares learning with dependent sampling ⋮ Error analysis for \(l^q\)-coefficient regularized moving least-square regression ⋮ Error analysis on Hérmite learning with gradient data ⋮ A reproducing kernel Hilbert space approach to high dimensional partially varying coefficient model ⋮ Statistical consistency of coefficient-based conditional quantile regression ⋮ Nonparametric regression using needlet kernels for spherical data ⋮ Multi-penalty regularization in learning theory ⋮ Generalization properties of doubly stochastic learning algorithms ⋮ Geometry on probability spaces ⋮ Regularization in kernel learning ⋮ Hermite learning with gradient data ⋮ Regularized least square regression with dependent samples ⋮ On the robustness of regularized pairwise learning methods based on kernels ⋮ Kernel-based conditional canonical correlation analysis via modified Tikhonov regularization ⋮ Multi-kernel regularized classifiers ⋮ An efficient kernel learning algorithm for semisupervised regression problems ⋮ ERM scheme for quantile regression ⋮ Sharp learning rates of coefficient-based \(l^q\)-regularized regression with indefinite kernels ⋮ Integral operator approach to learning theory with unbounded sampling ⋮ An oracle inequality for regularized risk minimizers with strongly mixing observations ⋮ Piecewise linear approximation methods with stochastic sampling sites ⋮ Radial basis function approximation of noisy scattered data on the sphere ⋮ Approximation by multivariate Bernstein-Durrmeyer operators and learning rates of least-squares regularized regression with multivariate polynomial kernels ⋮ Generalization errors of Laplacian regularized least squares regression ⋮ Learning gradients via an early stopping gradient descent method ⋮ Generalization bounds of ERM algorithm with Markov chain samples ⋮ Learning performance of Tikhonov regularization algorithm with geometrically beta-mixing observations ⋮ Convergence estimates in probability and in expectation for discrete least squares with noisy evaluations at random points ⋮ Learning theory approach to a system identification problem involving atomic norm ⋮ On the convergence rate of kernel-based sequential greedy regression ⋮ Approximation analysis of learning algorithms for support vector regression and quantile regression ⋮ On the regularized Laplacian eigenmaps ⋮ Laplacian twin support vector machine for semi-supervised classification ⋮ ERM learning with unbounded sampling ⋮ Error analysis for coefficient-based regularized regression in additive models ⋮ Sampling scattered data with Bernstein polynomials: stochastic and deterministic error estimates ⋮ Generalization bounds of ERM algorithm with \(V\)-geometrically ergodic Markov chains ⋮ 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 ⋮ Multivariate approximation for analytic functions with Gaussian kernels ⋮ Estimating conditional quantiles with the help of the pinball loss ⋮ Primal and dual model representations in kernel-based learning ⋮ On the empirical estimation of integral probability metrics ⋮ Gauss-Hermite quadratures for functions from Hilbert spaces with Gaussian reproducing kernels ⋮ Learning sparse gradients for variable selection and dimension reduction ⋮ Estimation of convergence rate for multi-regression learning algorithm ⋮ Semi-supervised learning with the help of Parzen windows ⋮ Dynamical memory control based on projection technique for online regression ⋮ Conditional quantiles with varying Gaussians ⋮ Online learning for quantile regression and support vector regression ⋮ Adaptive kernel methods using the balancing principle ⋮ The generalization performance of ERM algorithm with strongly mixing observations ⋮ Quantile regression with \(\ell_1\)-regularization and Gaussian kernels ⋮ Convergence rate of the semi-supervised greedy algorithm ⋮ Generalization ability of fractional polynomial models ⋮ Unified approach to coefficient-based regularized regression ⋮ Classification with non-i.i.d. sampling ⋮ Convergence analysis of an empirical eigenfunction-based ranking algorithm with truncated sparsity ⋮ Indefinite kernel network with \(l^q\)-norm regularization ⋮ Learning rate of support vector machine for ranking ⋮ Convergence rate of kernel canonical correlation analysis ⋮ Applied harmonic analysis and data processing. Abstracts from the workshop held March 25--31, 2018 ⋮ Introduction to the peptide binding problem of computational immunology: new results ⋮ Generalization performance of bipartite ranking algorithms with convex losses ⋮ Reproducing kernel Hilbert spaces associated with analytic translation-invariant Mercer kernels ⋮ Robust pairwise learning with Huber loss ⋮ Unregularized online learning algorithms with general loss functions ⋮ Perturbation of convex risk minimization and its application in differential private learning algorithms ⋮ Statistical performance of optimal scoring in reproducing kernel Hilbert spaces ⋮ Regularized kernel-based reconstruction in generalized Besov spaces ⋮ A numerical algorithm for zero counting. I: Complexity and accuracy ⋮ Learning and approximation by Gaussians on Riemannian manifolds ⋮ The convergence rate for a \(K\)-functional in learning theory ⋮ Support vector machines regression with \(l^1\)-regularizer ⋮ Consistency of regularized spectral clustering ⋮ Logistic classification with varying gaussians ⋮ Learning from non-identical sampling for classification ⋮ Moving least-square method in learning theory ⋮ Classification with Gaussians and convex loss. II: Improving error bounds by noise conditions ⋮ A Kernel Multiple Change-point Algorithm via Model Selection ⋮ Learning rates of multi-kernel regularized regression ⋮ Learning errors of linear programming support vector regression ⋮ Covering numbers of Gaussian reproducing kernel Hilbert spaces ⋮ Mercer theorem for RKHS on noncompact sets ⋮ Concentration estimates for the moving least-square method in learning theory ⋮ Semi-supervised learning based on high density region estimation ⋮ Coefficient-based \(l^q\)-regularized regression with indefinite kernels and unbounded sampling ⋮ Statistical analysis of the moving least-squares method with unbounded sampling ⋮ A sparse grid based method for generative dimensionality reduction of high-dimensional data ⋮ A note on application of integral operator in learning theory ⋮ Entropy and sampling numbers of classes of ridge functions ⋮ Learning from uniformly ergodic Markov chains ⋮ Debiased magnitude-preserving ranking: learning rate and bias characterization ⋮ Learning under \((1 + \epsilon)\)-moment conditions ⋮ Learning rates of least-square regularized regression with polynomial kernels ⋮ Estimates of the norm of the Mercer kernel matrices with discrete orthogonal transforms ⋮ Generalization performance of graph-based semi-supervised classification ⋮ SVD revisited: a new variational principle, compatible feature maps and nonlinear extensions ⋮ Capacity dependent analysis for functional online learning algorithms ⋮ Theory of deep convolutional neural networks. III: Approximating radial functions ⋮ Approximating smooth and sparse functions by deep neural networks: optimal approximation rates and saturation ⋮ Random sampling of signals concentrated on compact set in localized reproducing kernel subspace of \(L^p (\mathbb{R}^n)\) ⋮ Fully corrective gradient boosting with squared hinge: fast learning rates and early stopping ⋮ New Hilbert space tools for analysis of graph Laplacians and Markov processes ⋮ Robust partially linear trend filtering for regression estimation and structure discovery ⋮ Random average sampling in a reproducing kernel subspace of mixed Lebesgue space \(L^{p,q}(\mathbb{R}^{n+1})\) ⋮ Design of semi-tensor product-based kernel function for SVM nonlinear classification ⋮ Learning sparse and smooth functions by deep sigmoid nets ⋮ Rate of convergence of Stancu type modified \(q\)-Gamma operators for functions with derivatives of bounded variation ⋮ Error analysis of kernel regularized pairwise learning with a strongly convex loss ⋮ High-probability generalization bounds for pointwise uniformly stable algorithms ⋮ Random sampling and reconstruction in reproducing kernel subspace of mixed Lebesgue spaces ⋮ Learning rates of multitask kernel methods ⋮ On Szász-Durrmeyer type modification using Gould Hopper polynomials ⋮ Deep learning theory of distribution regression with CNNs ⋮ Learning performance of uncentered kernel-based principal component analysis ⋮ Coefficient-based regularized distribution regression ⋮ Online regularized learning algorithm for functional data ⋮ Random Sampling of Mellin Band-Limited Signals ⋮ Identifiability of interaction kernels in mean-field equations of interacting particles ⋮ Unsupervised learning of observation functions in state space models by nonparametric moment methods ⋮ Expected integration approximation under general equal measure partition ⋮ Error analysis of the moving least-squares method with non-identical sampling ⋮ Convergence bounds for empirical nonlinear least-squares ⋮ Analysis of the Generalization Error: Empirical Risk Minimization over Deep Artificial Neural Networks Overcomes the Curse of Dimensionality in the Numerical Approximation of Black--Scholes Partial Differential Equations ⋮ Some first results on the consistency of spatial regression with partial differential equation regularization ⋮ Learning theory of minimum error entropy under weak moment conditions ⋮ LOCAL LEARNING ESTIMATES BY INTEGRAL OPERATORS ⋮ Learning by atomic norm regularization with polynomial kernels ⋮ A Statistical Learning Approach to Modal Regression ⋮ The kernel regularized learning algorithm for solving Laplace equation with Dirichlet boundary ⋮ Distributed spectral pairwise ranking algorithms ⋮ Online regularized pairwise learning with non-i.i.d. observations ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Gradient descent for robust kernel-based regression ⋮ Operator-valued positive definite kernels and differentiable universality ⋮ Learning with Boundary Conditions ⋮ Error Analysis of Coefficient-Based Regularized Algorithm for Density-Level Detection ⋮ Weighted random sampling and reconstruction in general multivariate trigonometric polynomial spaces ⋮ Learning theory of distributed spectral algorithms ⋮ Consistency of learning algorithms using Attouch–Wets convergence ⋮ Regularized learning schemes in feature Banach spaces ⋮ Scenario Approach for Minmax Optimization with Emphasis on the Nonconvex Case: Positive Results and Caveats ⋮ On the K-functional in learning theory ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Learning rates for regularized least squares ranking algorithm ⋮ A STUDY ON THE ERROR OF DISTRIBUTED ALGORITHMS FOR BIG DATA CLASSIFICATION WITH SVM ⋮ Refined Rademacher Chaos Complexity Bounds with Applications to the Multikernel Learning Problem ⋮ Support vector machines regression with unbounded sampling ⋮ A Note on Support Vector Machines with Polynomial Kernels ⋮ Kernelized Elastic Net Regularization: Generalization Bounds, and Sparse Recovery ⋮ Online Pairwise Learning Algorithms ⋮ Robust Support Vector Machines for Classification with Nonconvex and Smooth Losses ⋮ Constrained ERM Learning of Canonical Correlation Analysis: A Least Squares Perspective ⋮ Learning Rates for Classification with Gaussian Kernels ⋮ Error bounds for approximations with deep ReLU neural networks in Ws,p norms ⋮ Random sampling and reconstruction in multiply generated shift-invariant spaces ⋮ On probabilistic convergence rates of stochastic Bernstein polynomials ⋮ Some Numerical Test on the Convergence Rates of Regression with Differential Regularization ⋮ Reproducing Properties of Differentiable Mercer-Like Kernels on the Sphere ⋮ Multivariate Monte Carlo Approximation Based on Scattered Data ⋮ Coefficient-based regularization network with variance loss for error ⋮ Chebyshev type inequality for stochastic Bernstein polynomials ⋮ Robust kernel-based distribution regression ⋮ Reproducing Properties of Holomorphic Kernels on Balls of ℂ^q ⋮ Hermite-Birkhoff Interpolation on Arbitrarily Distributed Data in Banach Spaces ⋮ Learning Rates of l^q Coefficient Regularization Learning with Gaussian Kernel ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Sampling and Stability ⋮ REGULARIZED LEAST SQUARE REGRESSION WITH SPHERICAL POLYNOMIAL KERNELS ⋮ LEARNING RATES OF REGULARIZED REGRESSION FOR FUNCTIONAL DATA ⋮ Learning Theory of Randomized Sparse Kaczmarz Method ⋮ Simultaneous estimations of optimal directions and optimal transformations for functional data ⋮ On the convergence rate and some applications of regularized ranking algorithms ⋮ Regularized modal regression with data-dependent hypothesis spaces ⋮ Randomized multi-scale kernels learning with sparsity constraint regularization for regression ⋮ A spectral series approach to high-dimensional nonparametric regression ⋮ ONLINE LEARNING WITH MARKOV SAMPLING ⋮ Nyström subsampling method for coefficient-based regularized regression ⋮ Online regularized pairwise learning with least squares loss ⋮ Performance analysis of the LapRSSLG algorithm in learning theory ⋮ Analysis of Regression Algorithms with Unbounded Sampling ⋮ Convergence Rates of Spectral Regularization Methods: A Comparison between Ill-Posed Inverse Problems and Statistical Kernel Learning ⋮ ANALYSIS OF CLASSIFICATION WITH A REJECT OPTION ⋮ Error Estimates for Multivariate Regression on Discretized Function Spaces ⋮ SVM LEARNING AND L^p APPROXIMATION BY GAUSSIANS ON RIEMANNIAN MANIFOLDS ⋮ Deep neural networks for rotation-invariance approximation and learning ⋮ Semi-supervised learning with summary statistics ⋮ Distributed learning with indefinite kernels ⋮ Optimal Rates for Multi-pass Stochastic Gradient Methods ⋮ VECTOR VALUED REPRODUCING KERNEL HILBERT SPACES AND UNIVERSALITY ⋮ Sparse additive machine with ramp loss ⋮ Reproducing Kernel Banach Spaces with the ℓ¹ Norm II: Error Analysis for Regularized Least Square Regression ⋮ Multikernel Regression with Sparsity Constraint ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Estimates of learning rates of regularized regression via polyline functions ⋮ New Insights Into Learning With Correntropy-Based Regression ⋮ A Framework of Learning Through Empirical Gain Maximization ⋮ Distributed Filtered Hyperinterpolation for Noisy Data on the Sphere ⋮ Optimal learning with Gaussians and correntropy loss ⋮ Unnamed Item ⋮ Unnamed Item ⋮ REPRODUCING KERNEL HILBERT SPACES OF FRACTAL INTERPOLATION FUNCTIONS FOR CURVE FITTING PROBLEMS ⋮ Error analysis of the kernel regularized regression based on refined convex losses and RKBSs ⋮ Thresholded spectral algorithms for sparse approximations ⋮ Approximating functions with multi-features by deep convolutional neural networks ⋮ Approximations of non-homogeneous Markov chains on abstract states spaces ⋮ Regularization: From Inverse Problems to Large-Scale Machine Learning ⋮ Learning Interaction Kernels in Mean-Field Equations of First-Order Systems of Interacting Particles ⋮ Analysis of k-partite ranking algorithm in area under the receiver operating characteristic curve criterion ⋮ Error analysis of the moving least-squares regression learning algorithm with β-mixing and non-identical sampling