scientific article; zbMATH DE number 7370593

Publication date: 9 July 2021

Full work available at URL: https://arxiv.org/abs/2004.08436

Title: zbMATH Open Web Interface contents unavailable due to conflicting licenses.

discrepancy principle reproducing kernel Hilbert space oracle inequality effective dimension early stopping non-parametric regression spectral regularization

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (3)

A note on the prediction error of principal component regression in high dimensions ⋮ Towards adaptivity via a new discrepancy principle for Poisson inverse problems ⋮ From inexact optimization to learning via gradient concentration

Cites Work

Unnamed Item
Unnamed Item
Unnamed Item
Unnamed Item
Unnamed Item
Unnamed Item
Unnamed Item
Regularization theory for ill-posed problems. Selected topics
Kernel ridge vs. principal component regression: minimax bounds and the qualification of regularization operators
Oracle inequalities in empirical risk minimization and sparse recovery problems. École d'Été de Probabilités de Saint-Flour XXXVIII-2008.
Optimal rates for regularization of statistical inverse learning problems
Variance estimation for high-dimensional regression models
On regularization algorithms in learning theory
Non-asymptotic adaptive prediction in functional linear models
Variance function estimation in multivariate nonparametric regression with fixed design
Early stopping for statistical inverse problems via truncated SVD estimation
A nearest neighbor estimate of the residual variance
A linear functional strategy for regularized ranking
A distribution-free theory of nonparametric regression
Weak convergence and empirical processes. With applications to statistics
Adaptive kernel methods using the balancing principle
Smoothed residual stopping for statistical inverse problems via truncated SVD estimation
Residual variance estimation using a nearest neighbor statistic
Optimal rates for spectral algorithms with least-squares regression over Hilbert spaces
High-probability bounds for the reconstruction error of PCA
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
On some extensions of Bernstein's inequality for self-adjoint operators
The discretized discrepancy principle under general source conditions
Shannon sampling. II: Connections to learning theory
Local Rademacher complexities
Boosting with early stopping: convergence and consistency
Learning theory estimates via integral operators and their approximations
On early stopping in gradient descent learning
On the mathematical foundations of learning
Convergence rates of Kernel Conjugate Gradient for random design regression
Discrepancy principle for statistical inverse problems with application to conjugate gradient iteration
Mathematical Foundations of Infinite-Dimensional Statistical Models
Support Vector Machines
CROSS-VALIDATION BASED ADAPTATION FOR REGULARIZATION OPERATORS IN LEARNING THEORY
A Technique for the Numerical Solution of Certain Integral Equations of the First Kind
Boosting With theL₂Loss
High-Dimensional Probability
Optimal Adaptation for Early Stopping in Statistical Inverse Problems
Neural Network Learning
Early Stopping for Kernel Boosting Algorithms: A General Analysis With Localized Complexities
An Introduction to Matrix Concentration Inequalities
Potential Functions in Mathematical Pattern Recognition
Theory of Reproducing Kernels
Introduction to nonparametric estimation
Boosting methods for regression

This page was built for publication: