Curvature, concentration and error estimates for Markov chain Monte Carlo
Joulin, Aldéric ; Ollivier, Yann
Ann. Probab., Tome 38 (2010) no. 1, p. 2418-2442 / Harvested from Project Euclid
We provide explicit nonasymptotic estimates for the rate of convergence of empirical means of Markov chains, together with a Gaussian or exponential control on the deviations of empirical means. These estimates hold under a “positive curvature” assumption expressing a kind of metric ergodicity, which generalizes the Ricci curvature from differential geometry and, on finite graphs, amounts to contraction under path coupling.
Publié le : 2010-11-15
Classification:  Markov chain Monte Carlo,  concentration of measure,  Ricci curvature,  Wasserstein distance,  65C05,  60J22,  62E17
@article{1285334210,
     author = {Joulin, Ald\'eric and Ollivier, Yann},
     title = {Curvature, concentration and error estimates for Markov chain Monte Carlo},
     journal = {Ann. Probab.},
     volume = {38},
     number = {1},
     year = {2010},
     pages = { 2418-2442},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1285334210}
}
Joulin, Aldéric; Ollivier, Yann. Curvature, concentration and error estimates for Markov chain Monte Carlo. Ann. Probab., Tome 38 (2010) no. 1, pp.  2418-2442. http://gdmltest.u-ga.fr/item/1285334210/