End-to-End Population Inference from Gravitational-Wave Strain using Transformers

TL;DR

Dingo-Pop is a transformer-based, simulation-driven framework that efficiently infers population properties from gravitational-wave data without traditional computational bottlenecks.

Contribution

It introduces a novel end-to-end population inference method using transformers trained on simulated data, bypassing per-event Bayesian sampling.

Findings

Achieves population inference in about one second per catalog.

Produces well-calibrated posteriors consistent with traditional Bayesian methods.

Enables large-scale studies of gravitational-wave populations and cosmological parameters.

Abstract

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.