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

Olivier Wintenberger (1, 2)

1 LSTA - Laboratoire de Statistique Théorique et Appliquée
2 UCPH - University of Copenhagen = Københavns Universitet

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].

Mots clés: Markov chains; exponential inequalities; Metropolis algorithm; Confidence inter-val

Domaines: Statistiques [math.ST]

Olivier Wintenberger. Exponential inequalities for unbounded functions of geometrically ergodic Markov chains. Applications to quantitative error bounds for regenerative Metropolis algorithms. Statistics, 2016, 51 (1), pp.222-234. ⟨10.1080/02331888.2016.1268205⟩. ⟨hal-01222870v2⟩