General Bernstein-like inequality for additive functionals of Markov chains
From MaRDI portal
Publication:2042045
Abstract: Using the renewal approach we prove Bernstein-like inequalities for additive functionals of geometrically ergodic Markov chains, thus obtaining counterparts of inequalities for sums of independent random variables. The coefficient in the sub-Gaussian part of our estimate is the asymptotic variance of the additive functional, i.e. the variance of the limiting Gaussian variable in the Central Limit Theorem for Markov chains. This refines earlier results by R. Adamczak and W. Bednorz, which were obtained under the additional assumption of strong aperiodicity of the chain.
Let \(Y = \left( {{Y_n},n \ge 1} \right)\) be a Markov chain with values in a measurable (countably generated) space. The chain \(Y\) is supposed to be \(\psi \)-irreducible and aperiodic and admitting a unique invariant probability measure. The paper gives consideration to tail inequalities \({P_x}\left( {\left| {\sum_{i = 0}^{n - 1} {f({Y_i})} } \right| > t} \right)\). Using the renewal approach, it establishes Bernstein-like inequalities for additive functionals of geometrically ergodic Markov chains.
Recommendations
- Exponential concentration inequalities for additive functionals of Markov chains
- New Bernstein and Hoeffding type inequalities for regenerative Markov chains
- Subgaussian concentration inequalities for geometrically ergodic Markov chains
- Sharp bounds for the tails of functionals of Markov chains
- Bernstein-type concentration inequalities for symmetric Markov processes
Cites work
- A Bernstein type inequality and moderate deviations for weakly dependent sequences
- A New Approach to the Limit Theory of Recurrent Markov Chains
- A regeneration proof of the central limit theorem for uniformly ergodic Markov chains
- A tail inequality for suprema of unbounded empirical processes with applications to Markov chains
- Bernstein-type concentration inequalities for symmetric Markov processes
- Bounds on regeneration times and limit theorems for subgeometric Markov chains
- Chernoff and Berry–Esséen inequalities for Markov processes
- Chernoff-type bound for finite Markov chains
- Concentration inequalities for Markov chains by Marton couplings and spectral methods
- Concentration of measure inequalities for Markov chains and \(\Phi\)-mixing processes.
- Deviation inequalities for sums of weakly dependent time series
- Exponential concentration inequalities for additive functionals of Markov chains
- General Irreducible Markov Chains and Non-Negative Operators
- scientific article; zbMATH DE number 5224738 (Why is no real title available?)
- Limit theorems for functionals of ergodic Markov chains with general state space
- Markov chains and stochastic stability
- Moment and probability inequalities for sums of bounded additive functionals of regular Markov chains via the Nummelin splitting technique
- New Bernstein and Hoeffding type inequalities for regenerative Markov chains
- On 1-dependent processes and k-block factors
- On degenerate sums of m-dependent variables
- Regenerative block-bootstrap for Markov chains
- Renewal theory and computable convergence rates for geometrically erdgodic Markov chains
- Strong approximation for additive functionals of geometrically ergodic Markov chains
- Subgaussian concentration inequalities for geometrically ergodic Markov chains
- Weak convergence and empirical processes. With applications to statistics
Cited in
(10)- A tail inequality for suprema of unbounded empirical processes with applications to Markov chains
- Adaptive invariant density estimation for continuous-time mixing Markov processes under sup-norm risk
- Exponential concentration inequalities for additive functionals of Markov chains
- Bernstein-type concentration inequalities for symmetric Markov processes
- Sharp bounds for the tails of functionals of Markov chains
- A generalization of Ueno's inequality for n-step transition probabilities
- New Bernstein and Hoeffding type inequalities for regenerative Markov chains
- Probability and moment inequalities for additive functionals of geometrically ergodic Markov chains
- Global central limit theorems for Markov chains
- Subgaussian concentration inequalities for geometrically ergodic Markov chains
This page was built for publication: General Bernstein-like inequality for additive functionals of Markov chains
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2042045)
