Prior-predictive value from fast growth simulations
Institut für Physik, Carl-von-Ossietzky-Universtität, 26111 Oldenburg, Germany
Published online: 19 April 2008
Building on a variant of the Jarzynski equation we propose a new method to numerically determine the prior-predictive value in a Bayesian inference problem. The method generalizes thermodynamic integration and is not hampered by equilibration problems. We demonstrate its operation by applying it to two simple examples and elucidate its performance. In the case of multi-modal posterior distributions the performance is superior to thermodynamic integration.
PACS: 02.50.-r – Probability theory, stochastic processes, and statistics / 02.50.Tt – Inference methods / 05.10.Ln – Monte Carlo methods
© EDP Sciences, Società Italiana di Fisica, Springer-Verlag, 2008