Saved in:
Bibliographic Details
Main Authors: Leyde, Konstantin, Green, Stephen R., Dax, Maximilian, Mould, Matthew, Fabbri, Cecilia Maria, Gair, Jonathan
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.11274
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916001829879808
author Leyde, Konstantin
Green, Stephen R.
Dax, Maximilian
Mould, Matthew
Fabbri, Cecilia Maria
Gair, Jonathan
author_facet Leyde, Konstantin
Green, Stephen R.
Dax, Maximilian
Mould, Matthew
Fabbri, Cecilia Maria
Gair, Jonathan
contents The population of compact binaries encodes information about their astrophysical origins and the expansion of the universe. Hierarchical Bayesian methods infer these properties by combining single-event posteriors. As catalogs grow, however, this approach becomes computationally expensive and is subject to increasing Monte Carlo uncertainty. We introduce Dingo-Pop, a simulation-based framework that infers population posteriors directly from gravitational-wave strain data. The data for each event are embedded into low-dimensional tokens and combined using a transformer trained on simulated catalogs subject to selection effects. This enables (i) population inference without per-event Monte Carlo sampling noise, (ii) amortization across variable catalog sizes using a single network, and (iii) end-to-end inference in about one second. We train a network for catalog sizes of 25 to 1000 events, and obtain well-calibrated posteriors consistent with traditional methods. By avoiding per-event analyses that can take hours to days, Dingo-Pop enables new classes of large-scale injection studies; as an application, we examine how spectral-siren Hubble constant uncertainties change with catalog size.
format Preprint
id arxiv_https___arxiv_org_abs_2605_11274
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle End-to-End Population Inference from Gravitational-Wave Strain using Transformers
Leyde, Konstantin
Green, Stephen R.
Dax, Maximilian
Mould, Matthew
Fabbri, Cecilia Maria
Gair, Jonathan
General Relativity and Quantum Cosmology
Cosmology and Nongalactic Astrophysics
High Energy Physics - Phenomenology
The population of compact binaries encodes information about their astrophysical origins and the expansion of the universe. Hierarchical Bayesian methods infer these properties by combining single-event posteriors. As catalogs grow, however, this approach becomes computationally expensive and is subject to increasing Monte Carlo uncertainty. We introduce Dingo-Pop, a simulation-based framework that infers population posteriors directly from gravitational-wave strain data. The data for each event are embedded into low-dimensional tokens and combined using a transformer trained on simulated catalogs subject to selection effects. This enables (i) population inference without per-event Monte Carlo sampling noise, (ii) amortization across variable catalog sizes using a single network, and (iii) end-to-end inference in about one second. We train a network for catalog sizes of 25 to 1000 events, and obtain well-calibrated posteriors consistent with traditional methods. By avoiding per-event analyses that can take hours to days, Dingo-Pop enables new classes of large-scale injection studies; as an application, we examine how spectral-siren Hubble constant uncertainties change with catalog size.
title End-to-End Population Inference from Gravitational-Wave Strain using Transformers
topic General Relativity and Quantum Cosmology
Cosmology and Nongalactic Astrophysics
High Energy Physics - Phenomenology
url https://arxiv.org/abs/2605.11274