Local convergence rates of the nonparametric least squares estimator with applications to transfer learning

DOI10.3150/23-BEJ1655MaRDI QIDQ6565304FDOQ6565304

Johannes Schmidt-Hieber, Petr Zamolodtchikov

Publication date: 2 July 2024

Published in: Bernoulli (Search for Journal in Brave)

nonparametric regression mean squared error transfer learning covariate shift nonparametric least squares minimax estimation domain adaptation local rates

Mathematics Subject Classification ID

Statistics (62-XX) Operations research, mathematical programming (90-XX)

Cites Work

Title not available (Why is that?)
Title not available (Why is that?)
Weak convergence and empirical processes. With applications to statistics
Maximum likelihood estimation of a log-concave density and its distribution function: basic properties and uniform consistency
Optimal rates of convergence for nonparametric estimators
Locally adaptive regression splines
High-Dimensional Statistics
Introduction to nonparametric estimation
Convergence rates of least squares regression estimators with heavy-tailed errors
Adaptive transfer learning
Transfer learning for nonparametric classification: minimax rate and adaptive classifier
The asymptotic behavior of monotone regression estimates
Improving predictive inference under covariate shift by weighting the log-likelihood function
A distribution-free theory of nonparametric regression
Maximum Likelihood Estimates of Monotone Parameters
Bounding the Smallest Singular Value of a Random Matrix Without Concentration
Learning Theory and Kernel Machines
Rates of convergence for minimum contrast estimators
Estimation of a convex function: Characterizations and asymptotic theory.
Estimating a regression function
On the Estimation of Parameters Restricted by Inequalities
On consistency in monotonic regression
Three notes on perfect linear sets
Smoothing Lipschitz functions
A regularity class for the roots of nonnegative functions
A Bayesian/information theoretic model of learning to learn via multiple task sampling
Regularization and the small-ball method. I: Sparse recovery
On deep learning as a remedy for the curse of dimensionality in nonparametric regression
Isotonic regression in general dimensions
Singular measures and the key of \(G\)
Distribution-free properties of isotonic regression
Adaptation to lowest density regions with application to support recovery
Nonparametric shape-restricted regression
Regularization and the small-ball method II: complexity dependent error rates
Nonparametric regression using deep neural networks with ReLU activation function
On the rate of convergence of fully connected deep neural network regression estimates
Set structured global empirical risk minimizers are rate optimal in general dimensions
Marginal singularity and the benefits of labels in covariate-shift
On the robustness of minimum norm interpolators and regularized empirical risk minimizers
On least squares estimation under heteroscedastic and heavy-tailed errors

This page was built for publication: Local convergence rates of the nonparametric least squares estimator with applications to transfer learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6565304)