Multivariate approximations in Wasserstein distance by Stein's method and Bismut's formula
Let \(X_t\) be the solution of the additive SDE \[dX_t=g(X_t)+\sqrt dB_t.\] Under the assumptions on the upper bound of the Hessian of \(g\) and the assumption that \(g\) has a contractive property, this Langevin SDE has a unique invariant probability measure \(\mu\). Take, e.g., \(g(x)=-c(1+|x|^2)^(p/2)x\). Let \(W\) be a random variable satisfying the following condition: there exists a copy \(W'\) of \(W\) such that \(E(W'-W|W)=\lambda (g(W)+R_1)\), \(E((W'-W)(W'-W)^T|W)=2\lambda (Id+R_2)\). The authors obtain an upper bound for the Wasserstein one distance between \(\mu\) and the law of \(W\) in terms of the above data, with which they also arrive at a sampling algorithm. The key intermediate results are gradient and higher derivative bounds on the solution of the Poisson equation/Stein's equation with right hand side a Lipschitz continuous function. A similar estimate is obtained in [\textit{J. Gorham} et al., Ann. Appl. Probab. 29, No. 5, 2884--2928 (2019; Zbl 1439.60073)] using a Bismut-Elworthy-Li formula [\textit{K. D. Elworthy} and \textit{X. M. Li}, J. Funct. Anal. 125, No. 1, 252--286 (1994; Zbl 0813.60049)] invoking higher regularity condition on \(g\). The authors apply instead the more versatile formulation: the integration by parts formula (the two formulas are now known to be equivalent for e.g. compact spaces, see [\textit{K. D. Elworthy} and \textit{X.-M. Li}, in: Itô's stochastic calculus and probability theory. Tribute dedicated to Kiyosi Itô on the occasion of his 80th birthday. Tokyo: Springer. 15--30 (1996; Zbl 0881.60052)]). They then use an explicit formula for the solution of the Poisson equation to obtain the necessary gradient and Hessian estimates. This non-normal approximation theorem can be considered as an extension of a result of \textit{S. Chatterjee} and \textit{Q.-M. Shao} [Ann. Appl. Probab. 21, No. 2, 464--483 (2011; Zbl 1216.60018)].
- Multivariate normal approximation using Stein's method and Malliavin calculus
- Stein's method for normal approximation in Wasserstein distances with application to the multivariate central limit theorem
- Stein's density method for multivariate continuous distributions
- The Wasserstein distance and approximation theorems
- Stein's method and multinomial approximation
- A high-dimensional CLT in \(\mathcal {W}_2\) distance with near optimal convergence rate
- A Lyapunov-type Bound in Rd
- A multivariate CLT for local dependence with \(n^{-1/2}\log n\) rate and applications to multivariate graph related statistics
- A note on the exchangeability condition in Stein's method
- Berry-Esseen bounds and Edgeworth expansions in the central limit theorem for transport distances
- Characterization of the convergence in total variation and extension of the fourth moment theorem to invariant measures of diffusions
- Diffusion models and steady-state approximations for exponentially ergodic Markovian queues
- Elliptic operators on \(\mathbb{R}^d\) with unbounded coefficients
- Ergodicity of the 2D Navier-Stokes equations with degenerate stochastic forcing
- Exponential and uniform ergodicity of Markov processes
- Exponential convergence of Langevin distributions and their discrete approximations
- Formulae for the derivatives of heat semigroups
- Gradient estimates for SDEs driven by multiplicative Lévy noise
- High-dimensional Bayesian inference via the unadjusted Langevin algorithm
- scientific article; zbMATH DE number 3900695 (Why is no real title available?)
- scientific article; zbMATH DE number 3986319 (Why is no real title available?)
- scientific article; zbMATH DE number 50805 (Why is no real title available?)
- scientific article; zbMATH DE number 1245556 (Why is no real title available?)
- scientific article; zbMATH DE number 3438144 (Why is no real title available?)
- scientific article; zbMATH DE number 2212010 (Why is no real title available?)
- Identifying the limiting distribution by a general approach of Stein's method
- Measuring sample quality with diffusions
- Multivariate normal approximation using exchangeable pairs
- Multivariate normal approximation using Stein's method and Malliavin calculus
- Multivariate normal approximation with Stein's method of exchangeable pairs under a general linearity condition
- Multivariate normal approximations by Stein's method and size bias couplings
- Multivariate Stein factors for a class of strongly log-concave distributions
- Nonnormal approximation by Stein's method of exchangeable pairs with application to the Curie-Weiss model
- Normal approximations with Malliavin calculus. From Stein's method to universality
- On the rate of convergence in the multivariate CLT
- On uniqueness of invariant measures for finite- and infinite-dimensional diffusions
- Quantitative Stability of the Entropy Power Inequality
- Reflection couplings and contraction rates for diffusions
- Second order PDE's in finite and infinite dimension
- Stein's method for steady-state diffusion approximations of \(\mathrm{M}/\mathrm{Ph}/n+\mathrm{M}\) systems
- Stein's method on Wiener chaos
- Stein's method, logarithmic Sobolev and transport inequalities
- The CLT in high dimensions: quantitative bounds via martingale embedding
- Theoretical Guarantees for Approximate Sampling from Smooth and Log-Concave Densities
- Wasserstein distance error bounds for the multivariate normal approximation of the maximum likelihood estimator
- Approximation to stochastic variance reduced gradient Langevin dynamics by stochastic delay differential equations
- Non-integrable stable approximation by Stein's method
- Central limit theorem and self-normalized Cramér-type moderate deviation for Euler-Maruyama scheme
- A kernel bound for non-symmetric stable distribution and its applications
- First-order covariance inequalities via Stein's method
- Stein's method for functions of multivariate normal random variables
- Donsker's theorem in Wasserstein-1 distance
- Stein's method for normal approximation in Wasserstein distances with application to the multivariate central limit theorem
- Correction to: Multivariate approximations in Wasserstein distance by Stein's method and Bismut's formula
- Stein factors for variance-gamma approximation in the Wasserstein and Kolmogorov distances
- Stein's method meets computational statistics: a review of some recent developments
- Multivariate Stein factors for a class of strongly log-concave distributions
- The Wasserstein distance and approximation theorems
- Stability estimates for invariant measures of diffusion processes, with applications to stability of moment measures and Stein kernels
- The prelimit generator comparison approach of Stein's method
- scientific article; zbMATH DE number 7662451 (Why is no real title available?)
- A probability approximation framework: Markov process approach
- Using Stein's method to analyze Euler-Maruyama approximations of regime-switching jump diffusion processes
- Stein's density method for multivariate continuous distributions
- Approximation of the invariant measure of stable SDEs by an Euler-Maruyama scheme
- Transportation onto log-Lipschitz perturbations
- Covariance representations, \(L^p\)-Poincaré inequalities, Stein's kernels, and high-dimensional CLTs
- A diffusion approach to Stein's method on Riemannian manifolds
- Multivariate stable approximation by Stein's method
- Variable-step Euler-Maruyama approximations of regime-switching jump diffusion processes
- Normalized and self-normalized Cramér-type moderate deviations for the Euler-Maruyama scheme for the SDE
- The Euler-Maruyama approximation of state-dependent regime switching diffusions
- Approximation of stable law in Wasserstein-1 distance by Stein's method
- Some notes on quantitative generalized CLTs with self-decomposable limiting laws by spectral methods
- Approximation of the invariant measure for stable stochastic differential equations by the Euler-Maruyama scheme with decreasing step sizes
- Gradient estimates for semigroups associated with stochastic differential equations driven by cylindrical Lévy processes
- Finite-sample bounds to the normal limit under group sequential sampling
- Optimal rates for ergodic SDEs driven by multiplicative -stable processes in Wasserstein-1 distance
- On the rate of convergence of the martingale central limit theorem in Wasserstein distances
- Existence and non-existence of the CLT for a family of SDEs driven by stable processes
- Stein's method for the matrix normal distribution
- \(\mathcal{W}_{\mathrm{d}}\)-convergence rate of EM schemes for invariant measures of supercritical stable SDEs
- Numerical approximation of invariant measures: a general framework and its application to discontinuous-drift SDEs
This page was built for publication: Multivariate approximations in Wasserstein distance by Stein's method and Bismut's formula
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2312685)
