Deep nonparametric regression on approximate manifolds: nonasymptotic error bounds with polynomial prefactors

DOI10.1214/23-AOS2266arXiv2104.06708OpenAlexW4380490515MaRDI QIDQ6172194

Guohao Shen, Yu Ling Jiao, Yuanyuan Lin, Unnamed Author

Publication date: 19 July 2023

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2104.06708

zbMATH Keywords

curse of dimensionalitylow-dimensional manifoldsapproximation errordeep neural networknonasymptotic error boundnetwork relative efficiency

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Nonparametric estimation (62G05) Artificial neural networks and deep learning (68T07)

Related Items (8)

Intrinsic and extrinsic deep learning on manifolds ⋮ Low dimensional approximation and generalization of multivariate functions on smooth manifolds using deep ReLU neural networks ⋮ Deep learning based on randomized quasi-Monte Carlo method for solving linear Kolmogorov partial differential equation ⋮ Recovering the source term in elliptic equation via deep learning: method and convergence analysis ⋮ Robust nonparametric regression based on deep ReLU neural networks ⋮ Nonasymptotic bounds for adversarial excess risk under misspecified models ⋮ Solving PDEs on spheres with physics-informed convolutional neural networks ⋮ Error analysis for empirical risk minimization over clipped ReLU networks in solving linear Kolmogorov partial differential equations

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Bayesian manifold regression
• A new approach to least-squares estimation, with applications
• Semi-supervised learning on Riemannian manifolds
• Estimating a regression function
• Nonparametric estimation of a probability density on a Riemannian manifold using Fourier expansions
• Random projections of smooth manifolds
• The dimensionality reduction principle for generalized additive models
• Nonparametric orthogonal series estimators of regression: A class attaining the optimal convergence rate in \(L_ 2\)
• Approximation of least squares regression on nested subspaces
• Nonparametric maximum likelihood estimation by the method of sieves
• Minimum contrast estimators on sieves: Exponential bounds and rates of convergence
• Rates of convergence for minimum contrast estimators
• The use of polynomial splines and their tensor products in multivariate function estimation. (With discussion)
• Convergence rate of sieve estimates
• Consistency for the least squares estimator in nonparametric regression
• Rate of convergence of nonparametric estimates of maximum-likelihood type
• Optimal global rates of convergence for nonparametric regression
• A distribution-free theory of nonparametric regression
• Weak convergence and empirical processes. With applications to statistics
• Limitations of the approximation capabilities of neural networks with one hidden layer
• On the rate of convergence of fully connected deep neural network regression estimates
• Optimal approximation rate of ReLU networks in terms of width and depth
• Nonlinear approximation via compositions
• Nonparametric regression using deep neural networks with ReLU activation function
• Error bounds for approximations with deep ReLU networks
• On deep learning as a remedy for the curse of dimensionality in nonparametric regression
• Minimax-optimal nonparametric regression in high dimensions
• Optimal smoothing in single-index models
• Estimating the reach of a manifold
• Regression on manifolds: estimation of the exterior derivative
• Finding the homology of submanifolds with high confidence from random samples
• Kernel density estimation on Riemannian manifolds
• Fractals in Probability and Analysis
• Curvature Measures
• Variable selection for the single-index model
• Topology and data
• Efficient agnostic learning of neural networks with bounded fan-in
• Direct Semiparametric Estimation of Single-Index Models with Discrete Covariates
• High-Dimensional Probability
• Laplacian Eigenmaps for Dimensionality Reduction and Data Representation
• Neural Network Learning
• Deep Neural Networks for Estimation and Inference
• Estimation of a Function of Low Local Dimensionality by Deep Neural Networks
• Deep Network Approximation for Smooth Functions
• Deep Network Approximation Characterized by Number of Neurons
• Local Linear Regression on Manifolds and Its Geometric Interpretation
• Nonlinear Dimensionality Reduction
• Hessian eigenmaps: Locally linear embedding techniques for high-dimensional data
• Testing the manifold hypothesis
• Nonparametric regression on low-dimensional manifolds using deep ReLU networks: function approximation and statistical recovery
• Convergence of stochastic processes

This page was built for publication: Deep nonparametric regression on approximate manifolds: nonasymptotic error bounds with polynomial prefactors