| Contents |
| One of the challenges in using Markov Chain Monte Carlo methods to sample from a target distribution is finding a good prior distribution. An ideal prior distribution would both be easy to sample from and have a high acceptance rate in the Metropolis step of the algorithm. This latter property ensures that the Markov chain will rapidly explore the configuration space under the target distribution. In this talk, we present work to use functionalized Gaussian priors which are preconditioned to minimize the distance, with respect to relative entropy, to the target measure. This will then be seen to give much more favorable sampling properties than the naive prior. |
|