On the mathematical foundations of learning

DOI10.1090/S0273-0979-01-00923-5zbMath0983.68162WikidataQ56387242 ScholiaQ56387242MaRDI QIDQ2761194

Felipe Cucker, Stephen Smale

Publication date: 17 December 2001

Published in: Bulletin of the American Mathematical Society (Search for Journal in Brave)

zbMATH Keywords

inductive inferenceapproximation to learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Coding and information theory (compaction, compression, models of communication, encoding schemes, etc.) (aspects in computer science) (68P30)

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

Tensors in computations ⋮ Random sampling in reproducing kernel spaces with mixed norm ⋮ Convergence and finite sample approximations of entropic regularized Wasserstein distances in Gaussian and RKHS settings ⋮ An Online Projection Estimator for Nonparametric Regression in Reproducing Kernel Hilbert Spaces ⋮ Consistency of Monte Carlo estimators for risk-neutral PDE-constrained optimization ⋮ Learning theory for inferring interaction kernels in second-order interacting agent systems ⋮ Semi-discrete Tikhonov regularization in RKHS with large randomly distributed noise ⋮ On the approximation of functions by tanh neural networks ⋮ Random sampling of signals concentrated on compact set in localized reproducing kernel subspace of \(L^p (\mathbb{R}^n)\) ⋮ Attaining the Chebyshev bound for optimal learning: a numerical algorithm ⋮ Robust optimal estimation of location from discretely sampled functional data ⋮ Unified Tests for Nonparametric Functions in RKHS With Kernel Selection and Regularization ⋮ Ultra-quantum coherent states in a single finite quantum system ⋮ Random average sampling in a reproducing kernel subspace of mixed Lebesgue space \(L^{p,q}(\mathbb{R}^{n+1})\) ⋮ Approximation Analysis of Convolutional Neural Networks ⋮ Learning dynamical systems from data: a simple cross-validation perspective. IV: Case with partial observations ⋮ Sparse machine learning in Banach spaces ⋮ A COLLOCATION METHOD FOR FREDHOLM INTEGRAL EQUATIONS OF THE FIRST KIND VIA ITERATIVE REGULARIZATION SCHEME ⋮ Overall error analysis for the training of deep neural networks via stochastic gradient descent with random initialisation ⋮ Learning sparse and smooth functions by deep sigmoid nets ⋮ Accelerating metabolic models evaluation with statistical metamodels: application to Salmonella infection models ⋮ Domain Generalization by Functional Regression ⋮ Learning system parameters from Turing patterns ⋮ Random sampling and reconstruction in reproducing kernel subspace of mixed Lebesgue spaces ⋮ Learning rates of multitask kernel methods ⋮ Gaussian kernels on nonsimply connected closed Riemannian manifolds are never positive definite ⋮ Nonexact oracle inequalities, \(r\)-learnability, and fast rates ⋮ On the coercivity condition in the learning of interacting particle systems ⋮ A duality approach to regularized learning problems in Banach spaces ⋮ Harmonic analysis of network systems via kernels and their boundary realizations ⋮ Sampling discretization error of integral norms for function classes with small smoothness ⋮ Deep learning theory of distribution regression with CNNs ⋮ Ensemble forecasts in reproducing kernel Hilbert space family ⋮ Random Sampling of Mellin Band-Limited Signals ⋮ Sample Size Estimates for Risk-Neutral Semilinear PDE-Constrained Optimization ⋮ A close look at the entropy numbers of the unit ball of the reproducing Hilbert space of isotropic positive definite kernels ⋮ Refined Rademacher Chaos Complexity Bounds with Applications to the Multikernel Learning Problem ⋮ Support vector machines regression with unbounded sampling ⋮ Refined Generalization Bounds of Gradient Learning over Reproducing Kernel Hilbert Spaces ⋮ FastMMD: Ensemble of Circular Discrepancy for Efficient Two-Sample Test ⋮ A Note on Support Vector Machines with Polynomial Kernels ⋮ Online Pairwise Learning Algorithms ⋮ Dimensionality-Dependent Generalization Bounds for k-Dimensional Coding Schemes ⋮ Generalization Analysis of Fredholm Kernel Regularized Classifiers ⋮ Random sampling and reconstruction in multiply generated shift-invariant spaces ⋮ Generalized Mercer Kernels and Reproducing Kernel Banach Spaces ⋮ Fluctuation-Dissipation Theorem and Models of Learning ⋮ A classification method based on generalized eigenvalue problems ⋮ Some properties of Gaussian reproducing kernel Hilbert spaces and their implications for function approximation and learning theory ⋮ Learning with Kernels and Logical Representations ⋮ Rejoinder ⋮ Minimum norm interpolation in the ℓ1(ℕ) space ⋮ Finite Sample Approximations of Exact and Entropic Wasserstein Distances Between Covariance Operators and Gaussian Processes ⋮ Approximative Policy Iteration for Exit Time Feedback Control Problems Driven by Stochastic Differential Equations using Tensor Train Format ⋮ Stochastic Difference-of-Convex-Functions Algorithms for Nonconvex Programming ⋮ Grothendieck bound in a single quantum system ⋮ Optimal sampling points in reproducing kernel Hilbert spaces ⋮ Regularized linear system identification using atomic, nuclear and kernel-based norms: the role of the stability constraint ⋮ Generalization performance of Lagrangian support vector machine based on Markov sampling ⋮ Gaussian approximations in high dimensional estimation ⋮ Multi-penalty regularization in learning theory ⋮ Accuracy of suboptimal solutions to kernel principal component analysis ⋮ Weyl eigenvalue asymptotics and sharp adaptation on vector bundles ⋮ Geometry on probability spaces ⋮ Nonparametric stochastic approximation with large step-sizes ⋮ Efficiency of classification methods based on empirical risk minimization ⋮ Upper bounds for errors of estimators in a problem of nonparametric regression: the adaptive case and the case of unknown measure \(\rho _X\) ⋮ Regularization in kernel learning ⋮ Entropy numbers of functions on \([-1,1\) with Jacobi weights] ⋮ Nonlinear projection recovery in digital inpainting for color image restoration ⋮ Terminated Ramp--Support Vector machines: A nonparametric data dependent kernel ⋮ Input estimation in nonlinear dynamical systems using differential algebra techniques ⋮ Nonlinear function approximation: computing smooth solutions with an adaptive greedy algorithm ⋮ Regression models for functional data by reproducing kernel Hilbert spaces methods ⋮ Distributed parametric and nonparametric regression with on-line performance bounds computation ⋮ On regularization algorithms in learning theory ⋮ Multi-kernel regularized classifiers ⋮ Learning rates of regularized regression on the unit sphere ⋮ Reproducing kernel Hilbert spaces associated with kernels on topological spaces ⋮ Universally consistent vertex classification for latent positions graphs ⋮ 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 ⋮ The learning rate of \(l_2\)-coefficient regularized classification with strong loss ⋮ Random sampling of bandlimited functions ⋮ Metamodeling the learning-hiding competition between tumours and the immune system: A kinematic approach ⋮ Least squares regression with \(l_1\)-regularizer in sum space ⋮ Approximation by multivariate Bernstein-Durrmeyer operators and learning rates of least-squares regularized regression with multivariate polynomial kernels ⋮ Functional analysis techniques to improve similarity matrices in discrimination problems ⋮ Comparing fixed and variable-width Gaussian networks ⋮ Estimates on compressed neural networks regression ⋮ Least square regression with indefinite kernels and coefficient regularization ⋮ 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 ⋮ A reproducing kernel Hilbert space approach to functional linear regression ⋮ Non-negativity constraints on the pre-image for pattern recognition with kernel machines ⋮ On complex-valued 2D eikonals. IV: continuation past a caustic ⋮ Prediction error identification of linear systems: a nonparametric Gaussian regression approach

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
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• On the parabolic kernel of the Schrödinger operator
• Multivariate interpolation at arbitrary points made simple
• Decision theoretic generalizations of the PAC model for neural net and other learning applications
• Smoothing noisy data with spline functions: Estimating the correct degree of smoothing by the method of generalized cross-validation
• Rates of convex approximation in non-Hilbert spaces
• Regularization networks and support vector machines
• A theory of the learnable
• COMPLEXITY AND REAL COMPUTATION: A MANIFESTO
• Generalization performance of regularization networks and support vector machines via entropy numbers of compact operators
• The importance of convexity in learning with squared loss
• Newton's method for overdetermined systems of equations
• PIECEWISE-POLYNOMIAL APPROXIMATIONS OF FUNCTIONS OF THE CLASSES $ W_{p}^{\alpha}$
• Theory of Reproducing Kernels
• A logical calculus of the ideas immanent in nervous activity
• Convergence of stochastic processes

This page was built for publication: On the mathematical foundations of learning