Enregistré dans:
Détails bibliographiques
Auteurs principaux: Scheutwinkel, Kilian H., Handley, Will, Weniger, Christoph, Acedo, Eloy de Lera
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2512.08316
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909950917214208
author Scheutwinkel, Kilian H.
Handley, Will
Weniger, Christoph
Acedo, Eloy de Lera
author_facet Scheutwinkel, Kilian H.
Handley, Will
Weniger, Christoph
Acedo, Eloy de Lera
contents We present PolySwyft, a novel, non-amortised simulation-based inference framework that unites the strengths of nested sampling (NS) and neural ratio estimation (NRE) to tackle challenging posterior distributions when the likelihood is intractable but a forward simulator is available. By nesting rounds of NRE within the exploration of NS, and employing a principled KL-divergence criterion to adaptively terminate sampling, PolySwyft achieves faster convergence on complex, multimodal targets while rigorously preserving Bayesian validity. On a suite of toy problems with analytically known posteriors of a dim(theta,D)=(5,100) multivariate Gaussian and multivariate correlated Gaussian mixture model, we demonstrate that PolySwyft recovers all modes and credible regions with fewer simulator calls than swyft's TNRE. As a real-world application, we infer cosmological parameters dim(theta,D)=(6,111) from CMB power spectra using CosmoPower. PolySwyft is released as open-source software, offering a flexible toolkit for efficient, accurate inference across the astrophysical sciences and beyond.
format Preprint
id arxiv_https___arxiv_org_abs_2512_08316
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PolySwyft: sequential simulation-based nested sampling
Scheutwinkel, Kilian H.
Handley, Will
Weniger, Christoph
Acedo, Eloy de Lera
Instrumentation and Methods for Astrophysics
Cosmology and Nongalactic Astrophysics
We present PolySwyft, a novel, non-amortised simulation-based inference framework that unites the strengths of nested sampling (NS) and neural ratio estimation (NRE) to tackle challenging posterior distributions when the likelihood is intractable but a forward simulator is available. By nesting rounds of NRE within the exploration of NS, and employing a principled KL-divergence criterion to adaptively terminate sampling, PolySwyft achieves faster convergence on complex, multimodal targets while rigorously preserving Bayesian validity. On a suite of toy problems with analytically known posteriors of a dim(theta,D)=(5,100) multivariate Gaussian and multivariate correlated Gaussian mixture model, we demonstrate that PolySwyft recovers all modes and credible regions with fewer simulator calls than swyft's TNRE. As a real-world application, we infer cosmological parameters dim(theta,D)=(6,111) from CMB power spectra using CosmoPower. PolySwyft is released as open-source software, offering a flexible toolkit for efficient, accurate inference across the astrophysical sciences and beyond.
title PolySwyft: sequential simulation-based nested sampling
topic Instrumentation and Methods for Astrophysics
Cosmology and Nongalactic Astrophysics
url https://arxiv.org/abs/2512.08316