Transportation-information inequalities for Markov processes
نویسندگان
چکیده
منابع مشابه
Transportation-information inequalities for Markov processes
In this paper, one investigates the following type of transportation-information TcI inequalities: α(Tc(ν, μ)) ≤ I(ν|μ) for all probability measures ν on some metric space (X , d), where μ is a given probability measure, Tc(ν, μ) is the transportation cost from ν to μ with respect to some cost function c(x, y) on X , I(ν|μ) is the FisherDonsker-Varadhan information of ν with respect to μ and α ...
متن کاملTransportation-information Inequalities for Markov Processes (ii) : Relations with Other Functional Inequalities
We continue our investigation on the transportation-information inequalities WpI for a symmetric markov process, introduced and studied in [14]. We prove that WpI implies the usual transportation inequalities WpH, then the corresponding concentration inequalities for the invariant measure μ. We give also a direct proof that the spectral gap in the space of Lipschitz functions for a diffusion pr...
متن کاملConcentration inequalities for Markov processes via coupling
We obtain moment and Gaussian bounds for general Lipschitz functions evaluated along the sample path of a Markov chain. We treat Markov chains on general (possibly unbounded) state spaces via a coupling method. If the first moment of the coupling time exists, then we obtain a variance inequality. If a moment of order 1+ ǫ of the coupling time exists, then depending on the behavior of the statio...
متن کاملBernstein type’s concentration inequalities for symmetric Markov processes
Using the method of transportation-information inequality introduced in [28], we establish Bernstein type’s concentration inequalities for empirical means 1 t ∫ t 0 g(Xs)ds where g is a unbounded observable of the symmetric Markov process (Xt). Three approaches are proposed : functional inequalities approach ; Lyapunov function method ; and an approach through the Lipschitzian norm of the solut...
متن کاملChernoff and Berry–esséen Inequalities for Markov Processes
In this paper, we develop bounds on the distribution function of the empirical mean for general ergodic Markov processes having a spectral gap. Our approach is based on the perturbation theory for linear operators, following the technique introduced by Gillman. Mathematics Subject Classification. 60F10. Received February 19, 2001. Revised September 21 and October 1, 2001.
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Probability Theory and Related Fields
سال: 2008
ISSN: 0178-8051,1432-2064
DOI: 10.1007/s00440-008-0159-5