Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Fast likelihood-free cosmology with neural density estimators and active learning
Stockholm University, Faculty of Science, Department of Physics. Stockholm University, Faculty of Science, The Oskar Klein Centre for Cosmo Particle Physics (OKC). Flatiron Institute, USA; Imperial College London, UK.
Number of Authors: 42019 (English)In: Monthly notices of the Royal Astronomical Society, ISSN 0035-8711, E-ISSN 1365-2966, Vol. 488, no 3, p. 4440-4458Article in journal (Refereed) Published
Abstract [en]

Likelihood-free inference provides a framework for performing rigorous Bayesian inference using only forward simulations, properly accounting for all physical and observational effects that can be successfully included in the simulations, The key challenge for likelihood-free applications in cosmology, where simulation is typically expensive, is developing methods that can achieve high-fidelity posterior inference with as few simulations as possible. Density estimation likelihood-free inference (DELFI) methods turn inference into a density-estimation task on a set of simulated data-parameter pairs, and give orders of magnitude improvements over traditional Approximate Bayesian Computation approaches to likelihood-free inference. In this paper, we use neural density estimators (NDEs) to learn the likelihood function from a set of simulated data sets, with active learning to adaptively acquire simulations in the most relevant regions of parameter space on the fly. We demonstrate the approach on a number of cosmological case studies, showing that for typical problems high-fidelity posterior inference can be achieved with just 0(103) simulations or fewer. In addition to enabling efficient simulation-based inference, for simple problems where the form of the likelihood is known, DELFI offers a fast alternative to Markov Chain Monte Carlo (MCMC) sampling, giving orders of magnitude speed-up in some cases. Finally, we introduce PYDELFI a flexible public implementation of DELFI with NDFs and active learning - available at haps://github.com/justinalsing/pydelfi.

Place, publisher, year, edition, pages
2019. Vol. 488, no 3, p. 4440-4458
Keywords [en]
data analysis: methods
National Category
Physical Sciences
Identifiers
URN: urn:nbn:se:su:diva-174967DOI: 10.1093/mnras/stz1960ISI: 000485158400108OAI: oai:DiVA.org:su-174967DiVA, id: diva2:1364452
Available from: 2019-10-22 Created: 2019-10-22 Last updated: 2019-10-22Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full text

Search in DiVA

By author/editor
Alsing, JustinFeeney, Stephen
By organisation
Department of PhysicsThe Oskar Klein Centre for Cosmo Particle Physics (OKC)
In the same journal
Monthly notices of the Royal Astronomical Society
Physical Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 2 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf