Site Map
Contacts
Follow us on Facebook Follow us on Twitter YouTube channel
Centro de Astrofísica da Universidade do Porto

COSMOABC: Likelihood-free inference via Population Monte Carlo Approximate Bayesian Computation

E. E. O. Ishida, S. D. P. Vitenti, M. Penna-Lima, J. Cisewski, R. S. de Souza, A. M. M. Trindade, E. Cameron, V. C. Busti

Abstract
Approximate Bayesian Computation (ABC) enables parameter inference for complex physical systems in cases where the true likelihood function is unknown, unavailable, or computationally too expensive. It relies on the forward simulation of mock data and comparison between observed and synthetic catalogues. Here we present COSMOABC, a Python ABC sampler featuring a Population Monte Carlo variation of the original ABC algorithm, which uses an adaptive importance sampling scheme. The code is very flexible and can be easily coupled to an external simulator, while allowing to incorporate arbitrary distance and prior functions. As an example of practical application, we coupled COSMOABC with the NUMCOSMO library and demonstrate how it can be used to estimate posterior probability distributions over cosmological parameters based on measurements of galaxy clusters number counts without computing the likelihood function. COSMOABC is published under the GPLv3 license on PyPI and GitHub and documentation is available at http://goo.gl/SmB8EX.

Keywords
Galaxies: statistics - (cosmology:) large-scale structure of universe

Astronomy and Computing
Volume 13, Page 1
November 2015

>> PDF>> ADS>> DOI

Institute of Astrophysics and Space Sciences

Institute of Astrophysics and Space Sciences (IA) is a new but long anticipated research infrastructure with a national dimension. It embodies a bold but feasible vision for the development of Astronomy, Astrophysics and Space Sciences in Portugal, taking full advantage and fully realizing the potential created by the national membership of the European Space Agency (ESA) and the European Southern Observatory (ESO). IA resulted from the merging the two most prominent research units in the field in Portugal: the Centre for Astrophysics of the University of Porto (CAUP) and the Center for Astronomy and Astrophysics of the University of Lisbon (CAAUL). It currently hosts more than two-thirds of all active researchers working in Space Sciences in Portugal, and is responsible for an even greater fraction of the national productivity in international ISI journals in the area of Space Sciences. This is the scientific area with the highest relative impact factor (1.65 times above the international average) and the field with the highest average number of citations per article for Portugal.

Proceed on CAUP's website|Go to IA website