Stein's method, logarithmic Sobolev and transport inequalities

DOI10.1007/S00039-015-0312-0MaRDI QIDQ2339746zbMATH OpenOpenAlexFDO

Authors Ivan Nourdin, Giovanni Peccati, Michel Ledoux

Publication date 2 April 2015

Published in Geometric and Functional Analysis. GAFA (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1403.5855

zbMATH Keywords

entropynormal approximationconcentration inequalityFisher information\(\Gamma\)-calculuslogarithmic Sobolev inequalityStein discrepancytransport inequalityconvergence to equilibriumStein kernel

Mathematics Subject Classification ID

Convergence of probability measures (60B10) Inequalities; stochastic orderings (60E15) Measures of information, entropy (94A17) Inequalities involving derivatives and differential and integral operators (26D10)

Abstract: We develop connections between Stein's approximation method, logarithmic Sobolev and transport inequalities by introducing a new class of functional inequalities involving the relative entropy, the Stein kernel, the relative Fisher information and the Wasserstein distance with respect to a given reference distribution on $mathbb{R}^d$. For the Gaussian model, the results improve upon the classical logarithmic Sobolev inequality and the Talagrand quadratic transportation cost inequality. Further examples of illustrations include multidimensional gamma distributions, beta distributions, as well as families of log-concave densities. As a by-product, the new inequalities are shown to be relevant towards convergence to equilibrium, concentration inequalities and entropic convergence expressed in terms of the Stein kernel. The tools rely on semigroup interpolation and bounds, in particular by means of the iterated gradients of the Markov generator with invariant measure the distribution under consideration. In a second part, motivated by the recent investigation by Nourdin, Peccati and Swan on Wiener chaoses, we address the issue of entropic bounds on multidimensional functionals $F$ with the Stein kernel via a set of data on $F$ and its gradients rather than on the Fisher information of the density. A natural framework for this investigation is given by the Markov Triple structure $(E,mu,Gamma)$ in which abstract Malliavin-type arguments may be developed and extend the Wiener chaos setting.

Recommendations

• Weighted Poincaré inequalities, concentration inequalities and tail bounds related to Stein kernels in dimension one
• Generalization of an inequality by Talagrand and links with the logarithmic Sobolev inequality
• A variational approach to some transport inequalities
• Stein's density approach and information inequalities
• On logarithmic Sobolev inequalities. With a preface of Dominique Bakry and Michel Ledoux

Cites work

• scientific article; zbMATH DE number 2131215 (Why is no real title available?)
• scientific article; zbMATH DE number 50805 (Why is no real title available?)
• scientific article; zbMATH DE number 3894218 (Why is no real title available?)
• A new approach to strong embeddings
• Analysis and geometry of Markov diffusion operators
• Asymptotic independence of multiple Wiener-Itô integrals and the resulting limit laws
• Berry-Esseen bounds in the entropic central limit theorem
• Central limit theorems for multiple stochastic integrals and Malliavin calculus
• Chaos of a Markov operator and the fourth moment condition
• Closed form summation for classical distributions: variations on a theme of de Moivre
• Concentration inequalities. A nonasymptotic theory of independence
• Distributional and \(L^q\) norm inequalities for polynomials over convex bodies in \(\mathbb{R}^n\)
• Entropy and the fourth moment phenomenon
• Fisher information and the central limit theorem
• Fisher information inequalities and the central limit theorem
• Fluctuations of eigenvalues and second order Poincaré inequalities
• Fourth moment theorems for Markov diffusion generators
• Generalization of an inequality by Talagrand and links with the logarithmic Sobolev inequality
• Generalization of the Nualart-Peccati criterion
• L'algèbre de Lie des gradients itérés d'un générateur markovien---développements de moyennes et entropies
• Large deviations and the Malliavin calculus
• Matrix concentration inequalities via the method of exchangeable pairs
• Noncentral convergence of multiple integrals
• Normal Approximation by Stein’s Method
• Normal approximations with Malliavin calculus. From Stein's method to universality
• On the rate of convergence in the entropic central limit theorem
• On the rate of convergence in the multivariate CLT
• On the role of convexity in isoperimetry, spectral gap and concentration
• Optimal Transport
• Rate of convergence and Edgeworth-type expansion in the entropic central limit theorem
• Some inequalities satisfied by the quantities of information of Fisher and Shannon
• Stein's method and the zero bias transformation with application to simple random sampling
• Stein's method for concentration inequalities
• Stein's method for diffusion approximations
• The Malliavin Calculus and Related Topics
• The concentration of measure phenomenon
• The convolution inequality for entropy powers
• Transportation cost for Gaussian and other product measures
• Variational inequalities with examples and an application to the central limit theorem

Cited in

(54)

• The Brownian transport map
• Sharp high-dimensional central limit theorems for log-concave distributions
• Improved rates of convergence for the multivariate central limit theorem in Wasserstein distance
• Rates of Fisher information convergence in the central limit theorem for nonlinear statistics
• Stability for the logarithmic Sobolev inequality
• Multivariate approximations in Wasserstein distance by Stein's method and Bismut's formula
• Superconvergence phenomenon in Wiener chaoses
• Stability of the Bakry-Émery theorem on \(\mathbb{R}^n\)
• Ornstein–Uhlenbeck operators and semigroups
• The fourth moment theorem on the Poisson space
• Higher-order pathwise theory of fluctuations in stochastic homogenization
• Covariance inequalities for convex and log-concave functions
• Stein's method of normal approximation: some recollections and reflections
• High-dimensional central limit theorems by Stein's method
• Stein's method for normal approximation in Wasserstein distances with application to the multivariate central limit theorem
• Quantitative logarithmic Sobolev inequalities and stability estimates
• Stein approximation for functionals of independent random sequences
• Parametric Stein operators and variance bounds
• Stein's method meets computational statistics: a review of some recent developments
• Stein's density method for multivariate continuous distributions
• A stroll along the gamma
• A quantitative fourth moment theorem in free probability theory
• A regularity method for lower bounds on the Lyapunov exponent for stochastic differential equations
• Geometric sums, size biasing and zero biasing
• Scaling limit of the homogenization commutator for Gaussian coefficient fields
• Bounds on the Poincaré constant for convolution measures
• An inequality for relative entropy and logarithmic Sobolev inequalities in Euclidean spaces
• Eigenvalue inequalities for the Markov diffusion operator
• Recent advances in various fields of numerical probability
• From \(p\)-Wasserstein bounds to moderate deviations
• Optimal bounds in normal approximation for many interacting worlds
• Free Stein kernels and an improvement of the free logarithmic Sobolev inequality
• A family of wave equations with some remarkable properties
• Some inequalities on Riemannian manifolds linking entropy, Fisher information, Stein discrepancy and Wasserstein distance
• Approximation of stable law in Wasserstein-1 distance by Stein's method
• On infinite covariance expansions
• Wasserstein-\(p\) bounds in the central limit theorem under local dependence
• Weighted Poincaré inequalities, concentration inequalities and tail bounds related to Stein kernels in dimension one
• Relaxing the Gaussian assumption in shrinkage and SURE in high dimension
• Quantitative normal approximation of linear statistics of \(\beta \)-ensembles
• Malliavin-Stein method: a survey of some recent developments
• Stability estimates for invariant measures of diffusion processes, with applications to stability of moment measures and Stein kernels
• Stein meets Malliavin in normal approximation
• High-dimensional central limit theorems for homogeneous sums
• Stein's method of normal approximation for dynamical systems
• Wasserstein-2 bounds in normal approximation under local dependence
• Existence of Stein kernels under a spectral gap, and discrepancy bounds
• Higher-order Stein kernels for Gaussian approximation
• Bounds in \(L^1\) Wasserstein distance on the normal approximation of general M-estimators
• On Stein's method for multivariate self-decomposable laws with finite first moment
• Stein's density approach and information inequalities
• Stein kernels and moment maps
• A Stein deficit for the logarithmic Sobolev inequality
• Covariance representations, \(L^p\)-Poincaré inequalities, Stein's kernels, and high-dimensional CLTs

This page was built for publication: Stein's method, logarithmic Sobolev and transport inequalities

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2339746)