Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

Exponential inequalities for unbounded functions of geometrically ergodic Markov chains. Applications to quantitative error bounds for regenerative Metropolis algorithms

Abstract : The aim of this note is to investigate the concentration properties of unbounded functions of geometrically ergodic Markov chains. We derive concentration properties of centered functions with respect to the square of the Lyapunov's function in the drift condition satisfied by the Markov chain. We apply the new exponential inequalities to derive confidence intervals for MCMC algorithms. Quantitative error bounds are providing for the regenerative Metropolis algorithm of [5].
Document type :
Preprints, Working Papers, ...
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01222870
Contributor : Olivier Wintenberger <>
Submitted on : Friday, September 9, 2016 - 3:34:23 PM
Last modification on : Wednesday, June 12, 2019 - 3:30:03 PM

Files

MCrev.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01222870, version 2
  • ARXIV : 1511.01752

Citation

Olivier Wintenberger. Exponential inequalities for unbounded functions of geometrically ergodic Markov chains. Applications to quantitative error bounds for regenerative Metropolis algorithms. 2016. ⟨hal-01222870v2⟩

Share

Metrics

Record views

356

Files downloads

483