Transdimensional (reversible-jump) MCMC

MCMC over candidate models with parameter vectors of varying dimension. I'm interested in applying this theory in the context of Bayesian model selection over the space of graphical structures representing viable models for genetic circuits.

Peter Green's research page

Brooks, Giudici, Roberts (2003), Efficient construction of reversible jump Markov chain Monte Carlo proposal distributions, J. Royal Stat Soc B.