amazing Gibbs sampler
When playing with Peter Rossi’s bayesm R package during a visit of Jean-Michel Marin to Paris, last week, we came up with the above Gibbs outcome. The setting is a Gaussian mixture model with three components in dimension 5 and the prior distributions are standard conjugate. In this case, with 500 observations and 5000 Gibbs iterations, the Markov chain (for one component of one mean of the mixture) has two highly distinct regimes: one that revolves around the true value of the parameter, 2.5, and one that explores a much broader area (which is associated with a much smaller value of the component weight). What we found amazing is the Gibbs ability to entertain both regimes, simultaneously.
March 8, 2015 at 7:29 am
This is what happens when there is a mild phase transition that the sampler has happened to cope with. It would be interesting to confirm this suspicion.
February 19, 2015 at 6:06 am
[…] amazing Gibbs sampler. […]