We propose a novel method (floz), based on normalizing flows, to estimate the Bayesian evidence (and its numerical uncertainty) from a preexisting set of samples drawn from the unnormalized posterior distribution. We validate it on distributions whose evidence is known analytically, up to 15 parameter space dimensions, and compare with two state-of-the-art techniques for estimating the evidence: nested sampling (which computes the evidence as its main target) and a 𝑘-nearest-neighbors technique that produces evidence estimates from posterior samples. Provided representative samples from the target posterior are available, our method is more robust to posterior distributions with sharp features, especially in higher dimensions. For a simple multivariate Gaussian, we demonstrate its accuracy for up to 200 dimensions with 105 posterior samples. floz has wide applicability, e.g., to estimate evidence from variational inference, Markov chain Monte Carlo samples, or any other method that delivers samples and their likelihood from the unnormalized posterior density. As a physical application, we use floz to compute the Bayes factor for the presence of the first overtone in the ringdown signal of the gravitational wave data of GW150914, finding good agreement with nested sampling.

Bayesian evidence estimation from posterior samples with normalizing flows / Srinivasan, Rahul; Crisostomi, Marco; Trotta, Roberto; Barausse, Enrico; Breschi, Matteo. - In: PHYSICAL REVIEW D. - ISSN 2470-0010. - 110:12(2024), pp. 1-14. [10.1103/physrevd.110.123007]

Bayesian evidence estimation from posterior samples with normalizing flows

Srinivasan, Rahul;Crisostomi, Marco;Trotta, Roberto;Barausse, Enrico;Breschi, Matteo
2024-01-01

Abstract

We propose a novel method (floz), based on normalizing flows, to estimate the Bayesian evidence (and its numerical uncertainty) from a preexisting set of samples drawn from the unnormalized posterior distribution. We validate it on distributions whose evidence is known analytically, up to 15 parameter space dimensions, and compare with two state-of-the-art techniques for estimating the evidence: nested sampling (which computes the evidence as its main target) and a 𝑘-nearest-neighbors technique that produces evidence estimates from posterior samples. Provided representative samples from the target posterior are available, our method is more robust to posterior distributions with sharp features, especially in higher dimensions. For a simple multivariate Gaussian, we demonstrate its accuracy for up to 200 dimensions with 105 posterior samples. floz has wide applicability, e.g., to estimate evidence from variational inference, Markov chain Monte Carlo samples, or any other method that delivers samples and their likelihood from the unnormalized posterior density. As a physical application, we use floz to compute the Bayes factor for the presence of the first overtone in the ringdown signal of the gravitational wave data of GW150914, finding good agreement with nested sampling.
2024
110
12
1
14
123007
Srinivasan, Rahul; Crisostomi, Marco; Trotta, Roberto; Barausse, Enrico; Breschi, Matteo
File in questo prodotto:
File Dimensione Formato  
PhysRevD.110.123007.pdf

non disponibili

Tipologia: Versione Editoriale (PDF)
Licenza: Copyright dell'editore
Dimensione 2.63 MB
Formato Adobe PDF
2.63 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.11767/143510
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact