Transportation-information inequalities for Markov processes

DOI10.1007/S00440-008-0159-5zbMATH Open1169.60304arXiv0706.4193OpenAlexW1995600142MaRDI QIDQ2391174FDOQ2391174

Authors: Nian Yao, Arnaud Guillin, Christian Léonard, Liming Wu 

Publication date: 24 July 2009

Published in: Zeitschrift für Wahrscheinlichkeitstheorie und Verwandte Gebiete (Search for Journal in Brave)

Abstract: In this paper, one investigates the following type of transportation-information $T_{c}I$ inequalities: $alpha(T_c(u,mu))leI(u|mu)$ for all probability measures $u$ on some metric space $(XX,d)$, where $mu$ is a given probability measure, $T_c(u,mu)$ is the transportation cost from $u$ to $mu$ with respect to some cost function $c(x,y)$ on $X{X}^2$, $I(u|mu)$ is the Fisher-Donsker-Varadhan information of $u$ with respect to $mu$ and $alpha:[0,infty)o[0,infty]$ is some left continuous increasing function. Using large deviation techniques, it is shown that $T_{c}I$ is equivalent to some concentration inequality for the occupation measure of a $mu$-reversible ergodic Markov process related to $I(cdot|mu)$, a counterpart of the characterizations of transportation-entropy inequalities, recently obtained by Gozlan and L'eonard in the i.i.d. case . Tensorization properties of $T_{c}I$ are also derived.

Full work available at URL: https://arxiv.org/abs/0706.4193

Recommendations

• Transport-information inequalities for Markov chains
• A characterization of transportation-information inequalities for Markov processes in terms of dimension-free concentration
• Transportation cost-information inequalities and applications to random dynamical systems and diffusions.
• A large deviation approach to some transportation cost inequalities
• Transportation inequalities for Markov kernels and their applications

zbMATH Keywords

concentration inequalitytransportation costlog-Sobolev inequalitiesFisher-Donsker-Varadhan informationPoincaré inequalities

Mathematics Subject Classification ID

Large deviations (60F10) Inequalities; stochastic orderings (60E15) Diffusion processes (60J60) Continuous-time Markov processes on general state spaces (60J25) Inequalities involving derivatives and differential and integral operators (26D10) One-parameter semigroups and linear evolution equations (47D06)

Cites Work

• On Choosing and Bounding Probability Metrics
• Markov chains and stochastic stability
• The concentration of measure phenomenon
• Ricci curvature for metric-measure spaces via optimal transport
• On the geometry of metric measure spaces. I
• On the geometry of metric measure spaces. II
• Title not available (Why is that?)
• Title not available (Why is that?)
• Rate of convergence for ergodic continuous Markov processes: Lyapunov versus Poincaré
• Bounding \(\bar d\)-distance by informational divergence: A method to prove measure concentration
• Title not available (Why is that?)
• Generalization of an inequality by Talagrand and links with the logarithmic Sobolev inequality
• Hypercontractivity of Hamilton-Jacobi equations.
• Large and moderate deviations and exponential convergence for stochastic damping Hamiltonian systems.
• A large deviation approach to some transportation cost inequalities
• Eigenvalues, Inequalities, and Ergodic Theory
• Title not available (Why is that?)
• Superadditivity of Fisher's information and logarithmic Sobolev inequalities
• Exponential integrability and transportation cost related to logarithmic Sobolev inequalities
• Weighted Csiszár-Kullback-Pinsker inequalities and applications to transportation inequalities
• Subgeometric rates of convergence of \(f\)-ergodic strong Markov processes
• Transportation cost-information inequalities and applications to random dynamical systems and diffusions.
• Transportation cost for Gaussian and other product measures
• Asymptotic evaluation of certain markov process expectations for large time. IV
• Uniformly integrable operators and large deviations for Markov processes
• Essential spectral radius for Markov semigroups. I: Discrete time case
• A measure concentration inequality for contracting Markov chains
• A new Poisson-type deviation inequality for Markov jump processes with positive Wasserstein curvature
• Chernoff and Berry–Esséen inequalities for Markov processes
• Monge-Kantorovitch measure transportation and Monge-Ampère equation on Wiener space
• Characterization of Talagrand's like transportation-cost inequalities on the real line
• On quadratic transportation cost inequalities
• A deviation inequality for non-reversible Markov processes
• deviation bounds for additive functionals of markov processes
• Convex concentration inequalities and forward-backward stochastic calculus
• Title not available (Why is that?)

Cited In (50)

• Intertwining and commutation relations for birth-death processes
• Logarithmic Sobolev inequalities for harmonic measures on spheres
• Exact adaptive pointwise drift estimation for multidimensional ergodic diffusions
• Transportation inequalities for stochastic differential equations of pure jumps
• Strong modified transportation cost inequalities on \(k\)-concave probability measures with heavy tails
• Existence and transportation inequalities for fractional stochastic differential equations
• An averaging principle for two-time-scale stochastic functional differential equations
• Large deviations for Markov-modulated diffusion processes with rapid switching
• Transportation inequalities for hidden Markov chains and applications
• Coarse Ricci curvature of quantum channels
• Exponential convergence of fisher entropy for diffusion processes
• Transportation-information inequalities for continuum Gibbs measures
• Approximating a diffusion by a finite-state hidden Markov model
• Principal feature detection via \(\phi \)-Sobolev inequalities
• Uncertainty quantification for Markov processes via variational principles and functional inequalities
• Spectral gap, isoperimetry and concentration on trees
• A note on Talagrand's transportation inequality and logarithmic Sobolev inequality
• Concentration inequalities for additive functionals: a martingale approach
• Self-improvement of the Bakry-Emery criterion for Poincaré inequalities and Wasserstein contraction using variable curvature bounds
• Lipschitzian norm estimate of one-dimensional Poisson equations and applications
• Uniform Poincaré and logarithmic Sobolev inequalities for mean field particle systems
• Spectral gap and convex concentration inequalities for birth-death processes
• Curvature, concentration and error estimates for Markov chain Monte Carlo
• Exponential convergence in the Wasserstein metric \(W_1\) for one dimensional diffusions
• Heat flow and concentration of measure on directed graphs with a lower Ricci curvature bound
• Gradient estimates of Poisson equations on Riemannian manifolds and applications
• Transport-information inequalities for Markov chains
• Wasserstein contraction and Poincaré inequalities for elliptic diffusions with high diffusivity
• Lipschitzian norms and functional inequalities for birth-death processes
• Convergence to equilibrium in Wasserstein distance for Fokker-Planck equations
• Hypercontractivity and transport-information inequalities for Gaussian ARMA model
• Transportation inequalities for Markov kernels and their applications
• Semi log-concave Markov diffusions
• Convex concentration for some additive functionals of jump stochastic differential equations
• Logarithmic Sobolev, isoperimetry and transport inequalities on graphs
• A new kind of modified transportation cost inequalities and polynomial concentration inequalities
• Transportation cost-information inequalities and applications to random dynamical systems and diffusions.
• A variational approach to some transport inequalities
• A large deviation approach to some transportation cost inequalities
• The Kantorovich and variation distances between invariant measures of diffusions and nonlinear stationary Fokker-Planck-Kolmogorov equations
• A new Poisson-type deviation inequality for Markov jump processes with positive Wasserstein curvature
• A characterization of dimension free concentration in terms of transportation inequalities
• Convergence rates for rank-based models with applications to portfolio theory
• Logarithmic Sobolev inequalities for Moebius measures on spheres
• A characterization of transportation-information inequalities for Markov processes in terms of dimension-free concentration
• Transportation inequalities for non-globally dissipative SDEs with jumps via Malliavin calculus and coupling
• Quantitative approximate independence for continuous mean field Gibbs measures
• Polynomial bounds in the Ergodic theorem for one-dimensional diffusions and integrability of hitting times
• A new characterization of quadratic transportation-information inequalities
• The Poincaré inequality and quadratic transportation-variance inequalities

This page was built for publication: Transportation-information inequalities for Markov processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2391174)