An interruptible algorithm for perfect sampling via Markov chains
Fill, James Allen
Ann. Appl. Probab., Tome 8 (1998) no. 1, p. 131-162 / Harvested from Project Euclid
For a large class of examples arising in statistical physics known as attractive spin systems (e.g., the Ising model), one seeks to sample from a probability distribution $\pi$ on an enormously large state space, but elementary sampling is ruled out by the infeasibility of calculating an appropriate normalizing constant. The same difficulty arises in computer science problems where one seeks to sample randomly from a large finite distributive lattice whose precise size cannot be ascertained in any reasonable amount of time. ¶ The Markov chain Monte Carlo (MCMC) approximate sampling approach to such a problem is to construct and run "for a long time" a Markov chain with long-run distribution $\pi$. But determining how long is long enough to get a good approximation can be both analytically and empirically difficult. ¶ Recently, Propp and Wilson have devised an ingenious and efficient algorithm to use the same Markov chains to produce perfect (i.e., exact) samples from $\pi$. However, the running time of their algorithm is an unbounded random variable whose order of magnitude is typically unknown a priori and which is not independent of the state sampled, so a naive user with limited patience who aborts a long run of the algorithm will introduce bias. ¶ We present a new algorithm which (1) again uses the same Markov chains to produce perfect samples from $\pi$, but is based on a different idea (namely, acceptance/rejection sampling); and (2) eliminates user-impatience bias. Like the Propp-Wilson algorithm, the new algorithm applies to a general class of suitably monotone chains, and also (with modification) to "anti-monotone" chains. When the chain is reversible, naive implementation of the algorithm uses fewer transitions but more space than Propp-Wilson. When fine-tuned and applied with the aid of a typical pseudorandom number generator to an attractive spin system on n sites using a random site updating Gibbs sampler whose mixing time $\tau$ is polynomial in n, the algorithm runs in time of the same order (bound) as Propp-Wilson [expectation $O(\tau \log n)$] and uses only logarithmically more space [expectation $O(n \log n)$, vs.$O9n)$ for Propp-Wilson].
Publié le : 1998-02-14
Classification:  Markov chain Monte Carlo,  perfect simulation,  rejection sampling,  monotone chain,  attractive spin system,  Ising model,  Gibbs sampler,  separation,  strong stationary time,  duality,  partially ordered set,  60J10,  68U20,  60G40,  62D05
@article{1027961037,
     author = {Fill, James Allen},
     title = {An interruptible algorithm for perfect sampling via Markov
		 chains},
     journal = {Ann. Appl. Probab.},
     volume = {8},
     number = {1},
     year = {1998},
     pages = { 131-162},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1027961037}
}
Fill, James Allen. An interruptible algorithm for perfect sampling via Markov
		 chains. Ann. Appl. Probab., Tome 8 (1998) no. 1, pp.  131-162. http://gdmltest.u-ga.fr/item/1027961037/