Concentration inequalities, large and moderate deviations for self-normalized empirical processes
Let \((X_n)_{n\geq 1}\) be a sequence of independent and identically distributed random variables in some measurable space \(X\), and let \(\mathcal{F}\) be a class of real-valued measurable functions on \(X\) which are centered and normalized, i.e. \(E(f(X_1))=0\) and \(E(f^2(X_1))=1\) for all \(f\in\mathcal{F}\). Let \(P_n=n^{-1}\sum_{k=1}^n\delta_{X_k}\) denote the empirical measure based on the observations \(X_1,\dots,X_n\), and consider the self-normalized empirical process \(W_n(f)=P_n(f)/\sqrt{P_n(f^2)}\) indexed by \(f\in\mathcal{F}\). For the supremum \({\mathcal W}_n=\sup_{f\in\mathcal{F}}W_n(f)\) of \(W_n\) an exponential concentration inequality is proven for certain classes \(\mathcal{F}\) of unbounded functions. This inequality is applied to establish a moderate deviation principle for \({\mathcal W}_n\). Moreover, results on large deviations of \({\mathcal W}_n\) are obtained for some parametric classes \(\mathcal{F}\) of unbounded functions.
- Concentration inequalities for suprema of unbounded empirical processes
- New concentration inequalities for suprema of empirical processes
- Concentration inequalities and asymptotic results for ratio type empirical processes
- A local probability exponential inequality for the large deviation of an empirical process indexed by an unbounded class of functions and its application
- About the rate function in concentration inequalities for suprema of bounded empirical processes
- About the constants in Talagrand's concentration inequalities for empirical processes.
- An inequality for uniform deviations of sample averages from their means
- Asymptotic Statistics
- Central limit theorems for empirical measures
- Concentration inequalities for set-indexed empirical processes
- Concentration of measure and isoperimetric inequalities in product spaces
- Consistent estimation of the order of mixture models.
- Convergence of stochastic processes
- Decision theoretic generalizations of the PAC model for neural net and other learning applications
- Empirical processes and applications: An overview. (With discussion)
- scientific article; zbMATH DE number 193011 (Why is no real title available?)
- scientific article; zbMATH DE number 3463998 (Why is no real title available?)
- scientific article; zbMATH DE number 1246230 (Why is no real title available?)
- scientific article; zbMATH DE number 1149757 (Why is no real title available?)
- scientific article; zbMATH DE number 1158743 (Why is no real title available?)
- scientific article; zbMATH DE number 819196 (Why is no real title available?)
- Inégalités exponentielles pour les processus empiriques
- Large deviations, moderate deviations and LIL for empirical processes
- Likelihood ratio inequalities with applications to various mixtures
- New concentration inequalities in product spaces
- On Talagrand's deviation inequalities for product measures
- Self-normalized large deviations
- Sur les déviations modérées des sommes de variables aléatoires vectorielles indépendantes de même loi. (On moderate deviations of sums of independent and identically distributed vector valued random variables)
- Testing in locally conic models, and application to mixture models
- Testing the order of a model using locally conic parametrization: Population mixtures and stationary ARMA processes
- The central limit theorem and the law of iterated logarithm for empirical processes under local conditions
- Weak convergence and empirical processes. With applications to statistics
- Self-normalization: taming a wild population in a heavy-tailed world
- Relative deviation learning bounds and generalization with unbounded loss functions
- Concentration around the mean for maxima of empirical processes
- An almost sure central limit theorem for self-normalized weighted sums
- About the rate function in concentration inequalities for suprema of bounded empirical processes
- A local probability exponential inequality for the large deviation of an empirical process indexed by an unbounded class of functions and its application
- Solving optimal stopping problems via empirical dual optimization
This page was built for publication: Concentration inequalities, large and moderate deviations for self-normalized empirical processes
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1872304)
