Efficient and Robust Bayesian Inference

MultiNest is a Bayesian inference tool which calculates the evidence and explores the parameter space which may contain multiple posterior modes and pronounced (curving) degeneracies in moderately high dimensions.

MultiNest is being made available as a standalone sampler for generic use for any inference problem [Subject to some licence restrictions]. For use with the cosmological application cosmomc we are also releasing the required plug-in files. Both releases are available on our downloads section.

NEW:
(Jun 09) several bug fixes, constant efficiency mode, support for periodic boundary conditions, increased sampling efficiency
(Dec 08) mode separation & local evidence evaluation, improved parallelization

Download the latest paper astro-ph/0809.3437 or the original paper astro-ph/0704.3704

Contact Farhan Feroz for any MultiNest queries.

Web page maintained by Farhan Feroz .