Polynomial Time Perfect Sampler for Discretized Dirichlet Distribution [chapter]

Tomomi Matsui, Shuji Kijima
The Grammar of Technology Development  
In this paper, we propose a perfect (exact) sampling algorithm according to a discretized Dirichlet distribution. Our algorithm is a monotone coupling from the past algorithm, which is a Las Vegas type randomized algorithm. We propose a new Markov chain whose limit distribution is a discretized Dirichlet distribution. Our algorithm simulates transitions of the chain O(n 3 ln ∆) times where n is the dimension (the number of parameters) and 1/∆ is the grid size for discretization. Thus the
more » ... d bound does not depend on the magnitudes of parameters. In each transition, we need to sample a random variable according to a discretized beta distribution (2-dimensional Dirichlet distribution). To show the polynomiality, we employ the path coupling method carefully and show that our chain is rapidly mixing.
doi:10.1007/978-4-431-75232-5_13 fatcat:h7mvhkjpxjf37bzeqoropr6t4i