English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Many statistical models in cosmology can be simulated forwards but haveintractable likelihood functions. Likelihood-free inference methods allow us toperform Bayesian inference from these models using only forward simulations,free from any likelihood assumptions or approximations. Likelihood-freeinference generically involves simulating mock data and comparing to theobserved data; this comparison in data-space suffers from the curse ofdimensionality and requires compression of the data to a small number ofsummary statistics to be tractable. In this paper we use massiveasymptotically-optimal data compression to reduce the dimensionality of thedata-space to just one number per parameter, providing a natural and optimalframework for summary statistic choice for likelihood-free inference. Secondly,we present the first cosmological application of Density EstimationLikelihood-Free Inference (\textsc{delfi}), which learns a parameterized modelfor joint distribution of data and parameters, yielding both the parameterposterior and the model evidence. This approach is conceptually simple,requires less tuning than traditional Approximate Bayesian Computationapproaches to likelihood-free inference and can give high-fidelity posteriorsfrom orders of magnitude fewer forward simulations. As an additional bonus, itenables parameter inference and Bayesian model comparison simultaneously. Wedemonstrate Density Estimation Likelihood-Free Inference with massive datacompression on an analysis of the joint light-curve analysis supernova data, asa simple validation case study. We show that high-fidelity posterior inferenceis possible for full-scale cosmological data analyses with as few as $\sim10^4$ simulations, with substantial scope for further improvement,demonstrating the scalability of likelihood-free inference to large and complexcosmological datasets.

Massive optimal data compression and density estimation for scalable, likelihood-free inference in cosmology