The CLT in high dimensions: quantitative bounds via martingale embedding
From MaRDI portal
Publication:2212600
Abstract: We introduce a new method for obtaining quantitative convergence rates for the central limit theorem (CLT) in a high dimensional setting. Using our method, we obtain several new bounds for convergence in transportation distance and entropy, and in particular: (a) We improve the best known bound, obtained by the third named author, for convergence in quadratic Wasserstein transportation distance for bounded random vectors; (b) We derive the first non-asymptotic convergence rate for the entropic CLT in arbitrary dimension, for general log-concave random vectors; (c) We give an improved bound for convergence in transportation distance under a log-concavity assumption and improvements for both metrics under the assumption of strong log-concavity. Our method is based on martingale embeddings and specifically on the Skorokhod embedding constructed by the first named author.
The paper introduces a new method for obtaining quantitative convergence rates for the central limit theorem in a high-dimensional setting. The approach is based on martingale embeddings. The method is applied to derive new bounds for convergence in transportation distance and entropy. It improves the best known convergence rate in quadratic Wasserstein transportation distance for bounded random vectors. For general log-concave random vectors the authors derive a nonasymptotic convergence rate for the entropic CLT in an arbitrary dimension. In addition, they provide an improved bound for convergence in transportation distance under a log-concavity assumption and improvements under the assumption of strong log-concavity.
Recommendations
- A high-dimensional CLT in \(\mathcal {W}_2\) distance with near optimal convergence rate
- scientific article; zbMATH DE number 868185
- On the rate of convergence in the multidimensional CLT for martingales
- High-dimensional CLT: improvements, non-uniform extensions and large deviations
- On the convergence rate in martingale CLT in Hilbert spaces
Cites work
- A convex/log-concave correlation inequality for Gaussian measure and an application to abstract Wiener spaces
- A Lyapunov-type Bound in Rd
- Asymptotic constants for minimal distance in the central limit theorem
- Berry-Esseen bounds and Edgeworth expansions in the central limit theorem for transport distances
- Berry-Esseen bounds in the entropic central limit theorem
- Concavity of certain maps on positive definite matrices and applications to Hadamard products
- Concentration of mass on convex bodies
- Eldan's stochastic localization and tubular neighborhoods of complex-analytic sets
- Entropic approach to E. Rio's central limit theorem for W₂ transport distance
- Entropic CLT and phase transition in high-dimensional Wishart matrices
- Entropy and the central limit theorem
- Entropy jumps for isotropic log-concave random vectors and spectral gap
- Entropy jumps in the presence of a spectral gap
- Estimating the unseen, an \(n/\log(n)\)-sample estimator for entropy and support size, shown optimal via new CLTs
- Existence of Stein kernels under a spectral gap, and discrepancy bounds
- Fisher information inequalities and the central limit theorem
- Gaussian approximations and multiplier bootstrap for maxima of sums of high-dimensional random vectors
- Gaussian-width gradient complexity, reverse log-Sobolev inequalities and nonlinear large deviations
- scientific article; zbMATH DE number 3896050 (Why is no real title available?)
- scientific article; zbMATH DE number 3932149 (Why is no real title available?)
- scientific article; zbMATH DE number 3711090 (Why is no real title available?)
- scientific article; zbMATH DE number 3565829 (Why is no real title available?)
- scientific article; zbMATH DE number 1245556 (Why is no real title available?)
- scientific article; zbMATH DE number 1324223 (Why is no real title available?)
- scientific article; zbMATH DE number 1975219 (Why is no real title available?)
- scientific article; zbMATH DE number 3097461 (Why is no real title available?)
- Information and dimensionality of anisotropic random geometric graphs
- On the rate of convergence in the entropic central limit theorem
- On the rate of convergence in the multivariate CLT
- Rate of convergence and Edgeworth-type expansion in the entropic central limit theorem
- Refinements of the multidimensional central limit theorem and applications
- Regularization under diffusion and anticoncentration of the information content
- Representation formula for the entropy and functional inequalities
- Skorokhod embeddings via stochastic flows on the space of Gaussian measures
- Stein kernels and moment maps
- Stein's method for normal approximation in Wasserstein distances with application to the multivariate central limit theorem
- Stochastic differential equations. An introduction with applications.
- The Accuracy of the Gaussian Approximation to the Sum of Independent Variates
- The central limit problem for convex bodies
- Thin shell implies spectral gap up to polylog via a stochastic localization scheme
- Upper bounds for minimal distances in the central limit theorem
Cited in
(23)- Stability of Talagrand's Gaussian transport-entropy inequality via the Föllmer process
- Estimation of smooth functionals in high-dimensional models: bootstrap chains and Gaussian approximation
- New error bounds in multivariate normal approximations via exchangeable pairs with applications to Wishart matrices and fourth moment theorems
- Taming correlations through entropy-efficient measure decompositions with applications to mean-field approximation
- High-dimensional CLT: improvements, non-uniform extensions and large deviations
- High-dimensional central limit theorems by Stein's method
- Multivariate approximations in Wasserstein distance by Stein's method and Bismut's formula
- A high-dimensional CLT in \(\mathcal {W}_2\) distance with near optimal convergence rate
- A CLT for multi-dimensional martingale differences in a lexicographic order
- On the equivalence of statistical distances for isotropic convex measures
- A class of dimension-free metrics for the convergence of empirical measures
- Covariance representations, \(L^p\)-Poincaré inequalities, Stein's kernels, and high-dimensional CLTs
- Large-dimensional central limit theorem with fourth-moment error bounds on convex sets and balls
- Improved rates of convergence for the multivariate central limit theorem in Wasserstein distance
- Sharp high-dimensional central limit theorems for log-concave distributions
- The Brownian transport map
- Sequential Gaussian approximation for nonstationary time series in high dimensions
- Gaussian approximation for nonstationary time series with optimal rate and explicit construction
- q-moment Stein kernels: application to the rate of convergence in the multidimensional CLT
- Localization schemes: a framework for proving mixing bounds for Markov chains
- On the rate of convergence of the martingale central limit theorem in Wasserstein distances
- Beyond separability: convergence rate of vanishing viscosity approximations to mean field games via FBSDE stability
- Notes on the dimension dependence in high-dimensional central limit theorems for hyperrectangles
This page was built for publication: The CLT in high dimensions: quantitative bounds via martingale embedding
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2212600)
