Quantitative bounds on convergence of time-inhomogeneous Markov chains
Douc, R. ; Moulines, E. ; Rosenthal, Jeffrey S.
Ann. Appl. Probab., Tome 14 (2004) no. 1, p. 1643-1665 / Harvested from Project Euclid
Text on Project Euclid
PDF
Alt PDF
Convergence rates of Markov chains have been widely studied in recent years. In particular, quantitative bounds on convergence rates have been studied in various forms by Meyn and Tweedie [Ann. Appl. Probab. 4 (1994) 981–1101], Rosenthal [J. Amer. Statist. Assoc. 90 (1995) 558–566], Roberts and Tweedie [Stochastic Process. Appl. 80 (1999) 211–229], Jones and Hobert [Statist. Sci. 16 (2001) 312–334] and Fort [Ph.D. thesis (2001) Univ. Paris VI]. In this paper, we extend a result of Rosenthal [J. Amer. Statist. Assoc. 90 (1995) 558–566] that concerns quantitative convergence rates for time-homogeneous Markov chains. Our extension allows us to consider f-total variation distance (instead of total variation) and time-inhomogeneous Markov chains. We apply our results to simulated annealing.
Publié le : 2004-11-14
Classification:  Convergence rate,  coupling,  Markov chain Monte Carlo,  simulated annealing,  f-total variation,  60J27,  60J22 
@article{1099674073,
     author = {Douc, R. and Moulines, E. and Rosenthal, Jeffrey S.},
     title = {Quantitative bounds on convergence of time-inhomogeneous Markov chains},
     journal = {Ann. Appl. Probab.},
     volume = {14},
     number = {1},
     year = {2004},
     pages = { 1643-1665},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1099674073}
}

Douc, R.; Moulines, E.; Rosenthal, Jeffrey S. Quantitative bounds on convergence of time-inhomogeneous Markov chains. Ann. Appl. Probab., Tome 14 (2004) no. 1, pp.  1643-1665. http://gdmltest.u-ga.fr/item/1099674073/