Deep nonlinear sufficient dimension reduction

DOI10.1214/24-AOS2390MaRDI QIDQ6608686zbMATH OpenFDO

Authors Yinfeng Chen, Yu Ling Jiao, Rui Qiu, Zhou Yu

Publication date 20 September 2024

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

Full work available at URL https://doi.org/10.1214/24-AOS2390

zbMATH Keywords

deep neural networksgeneralized martingale difference divergencesufficient dimension reductionU-process

Mathematics Subject Classification ID

Prediction theory (aspects of stochastic processes) (60G25) Nonparametric regression and quantile regression (62G08) Estimation in multivariate analysis (62H12) Neural nets and related approaches to inference from stochastic processes (62M45)

Cites work

• A Class of Statistics with Asymptotically Normal Distribution
• A general theory for nonlinear sufficient dimension reduction: formulation and estimation
• A kernel-based measure for conditional mean dependence
• A new class of measures for testing independence
• Algorithmic Learning Theory
• An Adaptive Estimation of Dimension Reduction Space
• An RKHS formulation of the inverse regression dimension-reduction problem
• Asymptotics for kernel estimate of sliced inverse regression
• Comment
• Concentration inequalities and model selection. Ecole d'Eté de Probabilités de Saint-Flour XXXIII -- 2003.
• Conditional variance estimator for sufficient dimension reduction
• Contour regression: a general approach to dimension reduction
• Deep dimension reduction for supervised representation learning
• Deep network approximation characterized by number of neurons
• Detecting independence of random vectors: generalized distance covariance and Gaussian covariance
• Determining the Dimension in Sliced Inverse Regression and Related Methods
• Determining the Dimensionality in Sliced Inverse Regression
• Dimension reduction for nonelliptically distributed predictors
• Dimension Reduction Forests: Local Variable Importance Using Structured Random Forests
• Efficient estimation in sufficient dimension reduction
• Estimating the structural dimension of regressions via parametric inverse regression
• Expected conditional characteristic function-based measures for testing independence
• Fréchet sufficient dimension reduction for random objects
• Fusing sufficient dimension reduction with neural networks
• Generalized martingale difference divergence: detecting conditional mean independence with applications in variable screening
• High-dimensional statistics. A non-asymptotic viewpoint
• scientific article; zbMATH DE number 7625173 (Why is no real title available?)
• scientific article; zbMATH DE number 7064043 (Why is no real title available?)
• Local Rademacher complexities
• Martingale difference correlation and its use in high-dimensional variable screening
• Martingale Difference Divergence Matrix and Its Application to Dimension Reduction for Stationary Multivariate Time Series
• Measuring and testing dependence by correlation of distances
• Nonlinear sufficient dimension reduction for functional data
• Nonparametric regression using deep neural networks with ReLU activation function
• On Directional Regression for Dimension Reduction
• On estimation efficiency of the central mean subspace
• Optimal global rates of convergence for nonparametric regression
• Principal Hessian Directions Revisited
• Principal support vector machines for linear and nonlinear sufficient dimension reduction
• Reducing the Dimensionality of Data with Neural Networks
• Regression analysis under link violation
• Sliced Inverse Regression for Dimension Reduction
• Successive direction extraction for estimating the central subspace in a multiple-index regres\-sion
• Weak convergence and empirical processes. With applications to statistics

Cited in

(3)

• Generative semi-supervised classification
• Belted and Ensembled Neural Network for Linear and Nonlinear Sufficient Dimension Reduction
• On the foundational arguments of sufficient dimension reduction

This page was built for publication: Deep nonlinear sufficient dimension reduction

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6608686)