Geometric ergodicity of Rao and Teh's algorithm for Markov jump processes and CTBNs

TL;DR

This paper proves that Rao and Teh's MCMC algorithm for sampling from hidden Markov jump processes and CTBNs is geometrically ergodic, ensuring rapid convergence under certain conditions.

Contribution

The paper establishes the geometric ergodicity of Rao and Teh's algorithm for HJPs and CTBNs, providing theoretical guarantees of convergence.

Findings

Markov chain is geometrically ergodic

Establishes geometric drift condition towards a small set

Results apply to both HJPs and CTBNs

Abstract

Rao and Teh (2012, 2013) introduced an efficient MCMC algorithm for sampling from the posterior distribution of a hidden Markov jump process. The algorithm is based on the idea of sampling virtual jumps. In the present paper we show that the Markov chain generated by Rao and Teh's algorithm is geometrically ergodic. To this end we establish a geometric drift condition towards a small set. A similar result is also proved for a special version of the algorithm, used for probabilistic inference in Continuous Time Bayesian Networks.