A Metropolis-Hastings Sampling of Subtrees in Graphs

Abstract

This article presents two methods to sample uniform subtrees from graphs using Metropolis-Hastings algorithms. One method is an independent Metropolis-Hastings and the other one is a type of add-and-delete MCMC. In addition to the theoretical contributions, we present simulation studies which confirm the theoretical convergence results on our methods by monitoring the convergence of our Markov chains to the equilibrium distribution.