Improved rates of convergence for the multivariate central limit theorem in Wasserstein distance

DOI10.1214/24-EJP1134MaRDI QIDQ6595693zbMATH OpenFDO

Authors Thomas Bonis

Publication date 30 August 2024

Published in Electronic Journal of Probability (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.1214/24-EJP1134

zbMATH Keywords

\(p\)-Wasserstein distancecentral limit theoremmultivariate normal approximationStein's method

Mathematics Subject Classification ID

Central limit and other weak theorems (60F05) Approximations to statistical distributions (nonasymptotic) (62E17)

Review text

Let \(W_1,\ldots,W_n\) be independent and centred random variables on \(\mathbb{R}^d\), and \(W=W_1+\cdots+W_n\) their sum having an identity covariance matrix. The author establishes new bounds in the multivariate central limit theorem for \(W\) in Wasserstein distance of order \(p\geq2\) which improve on the rates available in the literature. The author conjectures that this rate is optimal in the case where the \(W_i\) are identically distributed with non-zero third moment, and their measure includes a continuous component. The proofs make use of Stein's method.

Recommendations

• Stein's method for normal approximation in Wasserstein distances with application to the multivariate central limit theorem
• Explicit rates of convergence in the multivariate CLT for nonlinear statistics
• Wasserstein-p bounds in the central limit theorem under local dependence
• The CLT in high dimensions: quantitative bounds via martingale embedding
• Central limit theorems for the Wasserstein distance between the empirical and the true distributions

Cites work

• A high-dimensional CLT in \(\mathcal {W}_2\) distance with near optimal convergence rate
• Asymptotic constants for minimal distance in the central limit theorem
• Berry-Esseen bounds and Edgeworth expansions in the central limit theorem for transport distances
• Existence of Stein kernels under a spectral gap, and discrepancy bounds
• From \(p\)-Wasserstein bounds to moderate deviations
• New error bounds in multivariate normal approximations via exchangeable pairs with applications to Wishart matrices and fourth moment theorems
• Optimum bounds for the distributions of martingales in Banach spaces
• Stein kernels and moment maps
• Stein's method for normal approximation in Wasserstein distances with application to the multivariate central limit theorem
• Stein's method, logarithmic Sobolev and transport inequalities

Cited in

(3)

• Wasserstein-p bounds in the central limit theorem under local dependence
• Covariance representations, \(L^p\)-Poincaré inequalities, Stein's kernels, and high-dimensional CLTs
• Asymptotic equivalence of locally stationary processes and bivariate Gaussian white noise

This page was built for publication: Improved rates of convergence for the multivariate central limit theorem in Wasserstein distance

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6595693)