Uniform bounds for norms of sums of independent random functions

DOI10.1214/10-AOP595zbMATH Open1238.60023arXiv0904.1950OpenAlexW3102019351MaRDI QIDQ653305FDOQ653305

Authors: Alexander Goldenshluger, O. V. Lepski 

Publication date: 9 January 2012

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

Abstract: In this paper, we develop a general machinery for finding explicit uniform probability and moment bounds on sub-additive positive functionals of random processes. Using the developed general technique, we derive uniform bounds on the ${mathbbL}_s$-norms of empirical and regression-type processes. Usefulness of the obtained results is illustrated by application to the processes appearing in kernel density estimation and in nonparametric estimation of regression functions.

Full work available at URL: https://arxiv.org/abs/0904.1950

Recommendations

• scientific article; zbMATH DE number 562296
• Uniform exponential bound for the normalized empirical process
• scientific article; zbMATH DE number 819196
• A uniform functional law of the logarithm for the local empirical process.
• Uniform bounds under increment conditions

zbMATH Keywords

nonparametric estimationregressionkernel density estimationempirical processesconcentration inequalities\(\mathbb L_s\)-normsub-additive functional

Mathematics Subject Classification ID

Density estimation (62G07) Nonparametric regression and quantile regression (62G08) Inequalities; stochastic orderings (60E15)

Cites Work

• Weak convergence and empirical processes. With applications to statistics
• Title not available (Why is that?)
• Risk bounds for model selection via penalization
• Sharper bounds for Gaussian and empirical processes
• A Bennett concentration inequality and its application to suprema of empirical processes
• About the constants in Talagrand's concentration inequalities for empirical processes.
• Weighted uniform consistency of kernel density estimators.
• Title not available (Why is that?)
• Title not available (Why is that?)
• Structural adaptation via \(\mathbb L_p\)-norm oracle inequalities
• Inequalities for the $r$th Absolute Moment of a Sum of Random Variables, $1 \leqq r \leqq 2$
• Concentration inequalities and asymptotic results for ratio type empirical processes
• Risk hull method and regularization by projections of ill-posed inverse problems
• An empirical process approach to the uniform consistency of kernel-type function estimators
• Combinatorial methods in density estimation
• Probability inequalities for empirical processes and a law of the iterated logarithm
• Some limit theorems for empirical processes (with discussion)
• Uniform central limit theorems for kernel density estimators
• Best constants in moment inequalities for linear combinations of independent and exchangeable random variables
• Universal pointwise selection rule in multivariate function estimation
• Exponential bounds for minimum contrast estimators
• Optimum bounds for the distributions of martingales in Banach spaces
• On the asymptotic normality of \(L_ p\)-norms of empirical functionals
• The \(L_1\)-norm density estimator process
• Inequalities for Distributions of Sums of Independent Random Vectors and Their Application to Estimating a Density

Cited In (19)

• Upper functions for \(\mathbb{L}_{p}\)-norms of Gaussian random fields
• Upper functions for positive random functionals. I: General setting and Gaussian random functions
• On adaptive minimax density estimation on \(\mathbb R^d\)
• Title not available (Why is that?)
• A new approach to estimator selection
• Bandwidth selection in kernel density estimation: oracle inequalities and adaptive minimax optimality
• Uniform bounds under increment conditions
• Structural adaptive deconvolution under \({\mathbb{L}_p}\)-losses
• Lower bound for the maximum of a stochastic process
• An upper bound for functions of estimators in high dimensions
• Title not available (Why is that?)
• Title not available (Why is that?)
• On the almost sure boundedness of norms of some empirical operators
• Oracle inequalities and upper bounds for kernel density estimators on manifolds and more general metric spaces
• \(\mathbb{L}_{p}\) adaptive estimation of an anisotropic density under independence hypothesis
• Anisotropic adaptive kernel deconvolution
• Bandwidth selection in kernel empirical risk minimization via the gradient
• A bound on the expected maximal deviation of averages from their means.
• Bounds on the Expectation of Functions of Martingales and Sums of Positive RV's in Terms of Norms of Sums of Independent Random Variables

This page was built for publication: Uniform bounds for norms of sums of independent random functions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q653305)