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

Autor(es)

Ishida, E. E. O. ^[1] ; Vitenti, S. D. P. ^[2] ; Penna-Lima, M. ^{[3, 4]} ; Cisewski, J. ^[5] ; de Souza, R. S. ^[6] ; Trindade, A. M. M. ^{[7, 8]} ; Cameron, E. ^[9] ; Busti, V. C. ^{[10, 11]} ; Collaboration, COIN

Afiliação do(s) autor(es):Mostrar menos -

^[1] Max Planck Inst Astrophys, Karl Schwarzschild Str 1, D-85748 Garching - Germany

^[2] Univ Paris 06, CNRS, UMR7095, GR&CO Inst Astrophys Paris, F-75014 Paris - France

^[3] Inst Nacl Pesquisas Espaciais, Div Astrofis, BR-12227010 Sao Jose Dos Campos, SP - Brazil

^[4] Univ Paris Diderot, CNRS, IN2P3, APC, AstroParticule & Cosmol, UMR7164, F-75013 Paris - France

^[5] Yale Univ, Dept Stat, New Haven, CT 06511 - USA

^[6] MTA Eotvos Univ, EIRSA Lendulet Astrophys Res Grp, H-1117 Budapest - Hungary

^[7] Univ Porto, Inst Astrofis & Ciencias Espaco, CAUP, P-4150762 Oporto - Portugal

^[8] Univ Porto, Fac Ciencias, Dept Fis & Astron, P-4169007 Oporto - Portugal

^[9] Univ Oxford, Dept Zool, Oxford OX1 3PS - England

^[10] Univ Cape Town, Dept Math & Appl Math, ACGC, ZA-7701 Rondebosch - South Africa

^[11] Univ Sao Paulo, Inst Fis, Dept Fis Matemat, BR-05508090 Sao Paulo, SP - Brazil

• Tipo de documento: Artigo Científico
• Fonte: ASTRONOMY AND COMPUTING; v. 13, p. 1-11, NOV 2015.
• Citações Web of Science: 29

Resumo

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. (C) 2015 Elsevier B.V. All rights reserved. (AU)

• Processo FAPESP: 14/21098-1 - Cosmologia de precisão com o Dark Energy Survey
• Beneficiário: Vinicius Consolini Busti
• Linha de fomento: Bolsas no Brasil - Pós-Doutorado