BibTeX

@article{2512.08316v1,
Author        = {Kilian H. Scheutwinkel and Will Handley and Christoph Weniger and Eloy de Lera Acedo},
Title         = {PolySwyft: sequential simulation-based nested sampling},
Eprint        = {2512.08316v1},
ArchivePrefix = {arXiv},
PrimaryClass  = {astro-ph.IM},
Abstract      = {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.},
Year          = {2025},
Month         = {Dec},
Url           = {http://arxiv.org/abs/2512.08316v1},
File          = {2512.08316v1.pdf}
}