Wasserstein-p bounds in the central limit theorem under local dependence
From MaRDI portal
Publication:6136841
DOI10.1214/23-EJP1009arXiv2307.04188OpenAlexW4387942748MaRDI QIDQ6136841FDOQ6136841
Publication date: 17 January 2024
Published in: Electronic Journal of Probability (Search for Journal in Brave)
Abstract: The central limit theorem (CLT) is one of the most fundamental results in probability; and establishing its rate of convergence has been a key question since the 1940s. For independent random variables, a series of recent works established optimal error bounds under the Wasserstein-p distance (with p>=1). In this paper, we extend those results to locally dependent random variables, which include m-dependent random fields and U-statistics. Under conditions on the moments and the dependency neighborhoods, we derive optimal rates in the CLT for the Wasserstein-p distance. Our proofs rely on approximating the empirical average of dependent observations by the empirical average of i.i.d. random variables. To do so, we expand the Stein equation to arbitrary orders by adapting the Stein's dependency neighborhood method. Finally we illustrate the applicability of our results by obtaining efficient tail bounds.
Full work available at URL: https://arxiv.org/abs/2307.04188
Central limit and other weak theorems (60F05) Approximations to statistical distributions (nonasymptotic) (62E17)
Cites Work
- Title not available (Why is that?)
- Title not available (Why is that?)
- Title not available (Why is that?)
- Title not available (Why is that?)
- Title not available (Why is that?)
- Title not available (Why is that?)
- A Class of Statistics with Asymptotically Normal Distribution
- Optimal Transport
- On the central limit theorem for stationary mixing random fields
- Positive Definite Matrices and Sylvester's Criterion
- A CENTRAL LIMIT THEOREM AND A STRONG MIXING CONDITION
- Normal convergence by higher semi-invariants with applications to sums of dependent random variables and random graphs
- The central limit theorem for dependent random variables
- Fundamentals of Stein's method
- Generalization of an inequality by Talagrand and links with the logarithmic Sobolev inequality
- Normal approximation for nonlinear statistics using a concentration inequality approach
- Normal approximation under local dependence.
- Indeterminate moment problems and the theory of entire functions
- Combinatorics of Compositions and Words
- Poisson approximation for dependent trials
- Stein's method, logarithmic Sobolev and transport inequalities
- New rates for exponential approximation and the theorems of Rényi and Yaglom
- Transportation cost for Gaussian and other product measures
- Exponential approximation by Stein's method and spectral graph theory
- A central limit theorem for decomposable random variables with applications to random graphs
- Upper bounds for minimal distances in the central limit theorem
- Asymptotic expansions based on smooth functions in the central limit theorem
- A method for the derivation of limit theorems for sums of m-dependent random variables
- On normal approximations of distributions in terms of dependency graphs
- Probability Metrics
- Stein's method for comparison of univariate distributions
- Distances minimales et distances idéales
- Stein's method for normal approximation in Wasserstein distances with application to the multivariate central limit theorem
- The fundamental limit theorems in probability
- Estimates for Global Central Limit Theorems
- Berry-Esseen bounds and Edgeworth expansions in the central limit theorem for transport distances
- Mod-ϕ Convergence
- The Central Limit Theorem for a Sequence of Random Variables with a Slowly Growing Number of Dependences
- Wasserstein-2 bounds in normal approximation under local dependence
This page was built for publication: Wasserstein-\(p\) bounds in the central limit theorem under local dependence
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6136841)
