Journal Article

BAMBI: blind accelerated multimodal Bayesian inference

Philip Graff, Farhan Feroz, Michael P. Hobson and Anthony Lasenby

in Monthly Notices of the Royal Astronomical Society

Published on behalf of The Royal Astronomical Society

Volume 421, issue 1, pages 169-180
Published in print March 2012 | ISSN: 0035-8711
Published online March 2012 | e-ISSN: 1365-2966 | DOI: http://dx.doi.org/10.1111/j.1365-2966.2011.20288.x
BAMBI: blind accelerated multimodal Bayesian inference

More Like This

Show all results sharing this subject:

  • Astronomy and Astrophysics

GO

Show Summary Details

Preview

In this paper, we present an algorithm for rapid Bayesian analysis that combines the benefits of nested sampling and artificial neural networks (NNs). The blind accelerated multimodal Bayesian inference (BAMBI) algorithm implements the MultiNest package for nested sampling as well as the training of an artificial NN to learn the likelihood function. In the case of computationally expensive likelihoods, this allows the substitution of a much more rapid approximation in order to increase significantly the speed of the analysis. We begin by demonstrating, with a few toy examples, the ability of an NN to learn complicated likelihood surfaces. BAMBI’s ability to decrease running time for Bayesian inference is then demonstrated in the context of estimating cosmological parameters from Wilkinson Microwave Anisotropy Probe and other observations. We show that valuable speed increases are achieved in addition to obtaining NNs trained on the likelihood functions for the different model and data combinations. These NNs can then be used for an even faster follow-up analysis using the same likelihood and different priors. This is a fully general algorithm that can be applied, without any pre-processing, to other problems with computationally expensive likelihood functions.

Keywords: methods: data analysis; methods: statistical; cosmological parameters

Journal Article.  8286 words.  Illustrated.

Subjects: Astronomy and Astrophysics

Full text: subscription required

How to subscribe Recommend to my Librarian

Users without a subscription are not able to see the full content. Please, subscribe or login to access all content.