Multivariate normal approximation using exchangeable pairs

Abstract

Since the introduction of Stein's method in the early 1970s, much research has been done in extending and strengthening it; however, there does not exist a version of Stein's original method of exchangeable pairs for multivariate normal approximation. The aim of this article is to fill this void. We present three abstract normal approximation theorems using exchangeable pairs in multivariate contexts, one for situations in which the underlying symmetries are discrete, and real and complex versions of a theorem for situations involving continuous symmetry groups. Our main applications are proofs of the approximate normality of rank $k$ projections of Haar measure on the orthogonal and unitary groups, when $k=o(n)$.

25 pages. Substantially revised to simplify proofs. Rates of convergence are improved and a new result on projections of the unitary group has been added

References in corpus (3)

• A new method of normal approximation
• Multivariate normal approximation with Stein's method of exchangeable pairs under a general linearity condition
• How many entries of a typical orthogonal matrix can be approximated by independent normals?

Cited by in corpus (53)

• Gaussian approximations and multiplier bootstrap for maxima of sums of high-dimensional random vectors
• Gaussian approximation of suprema of empirical processes
• Uniform Post Selection Inference for LAD Regression and Other Z-estimation problems
• A new method of normal approximation
• Multivariate normal approximation with Stein's method of exchangeable pairs under a general linearity condition
• Measuring Sample Quality with Stein's Method
• A short survey of Stein's method
• Berry-Esseen Bounds of Normal and Non-normal Approximation for Unbounded Exchangeable Pairs
• Stein's method in high dimensions with applications
• Multivariate Normal Approximation by Stein's Method: The Concentration Inequality Approach
• Fourth moment theorems on the Poisson space in any dimension
• Rate of convergence of linear functions on the unitary group
• Rates of convergence for multivariate normal approximation with applications to dense graphs and doubly indexed permutation statistics
• Asymptotic behavior of large Gaussian correlated Wishart matrices
• On Stein's Method for Multivariate Self-Decomposable Laws
• Rigorous Dynamics of Expectation-Propagation-Based Signal Recovery from Unitarily Invariant Measurements
• On the Neural Tangent Kernel of Deep Networks with Orthogonal Initialization
• Stein operators, kernels and discrepancies for multivariate continuous distributions
• A comparison principle for functions of a uniformly random subspace
• A multivariate central limit theorem for Lipschitz and smooth test functions
• Fourth Moment Theorems for complex Gaussian approximation
• Functional approximations with Stein's method of exchangeable pairs
• Wilson loop expectations in $SU(N)$ lattice gauge theory
• A diffusion approach to Stein's method on Riemannian manifolds
• Convergence of densities of some functionals of Gaussian processes
• De Finetti-Style Results for Wishart Matrices: Combinatorial Structure and Phase Transitions
• Regularity of solutions of the Stein equation and rates in the multivariate central limit theorem
• A CLT in Stein's distance for generalized Wishart matrices and higher order tensors
• A unified approach to Stein characterizations
• Stein's method on the second Wiener chaos : 2-Wasserstein distance
• Random matrices with prescribed eigenvalues and expectation values for random quantum states
• Entropy and the fourth moment phenomenon
• The rate of convergence of some asymptotically chi-square distributed statistics by Stein's method
• On Stein's Method for Multivariate Self-Decomposable Laws With Finite First Moment
• Rate optimality of Random walk Metropolis algorithm in high-dimension with heavy-tailed target distribution
• Stein's method for diffusive limit of queueing processes
• Stein's method and the multivariate CLT for traces of powers on the classical compact groups
• Stein's method for dynamical systems
• Quantitative normal approximation for sums of random variables with multilevel local dependence structure
• Stein's method and a quantitative Lindeberg CLT for the Fourier transforms of random vectors
• Total variation approximation of random orthogonal matrices by Gaussian matrices
• Dirichlet approximation of equilibrium distributions in Cannings models with mutation
• Spin glasses and Stein's method
• An approximation to steady-state of M/Ph/n+M queue
• Convergence in total variation on Wiener chaos
• Central limit theorems with a rate of convergence for sequences of transformations
• Quantitative CLTs for symmetric $U$-statistics using contractions
• A multivariate CLT for bounded decomposable random vectors with the best known rate
• Two multivariate central limit theorems
• Multivariate approximations in Wasserstein distance by Stein's method and Bismut's formula
• Multi-dimensional Gaussian fluctuations on the Poisson space
• Fluctuations of the spectrum in rotationally invariant random matrix ensembles
• Approximation of projections of random vectors