Group equivariant neural posterior estimation

Abstract

Simulation-based inference with conditional neural density estimators is a powerful approach to solving inverse problems in science. However, these methods typically treat the underlying forward model as a black box, with no way to exploit geometric properties such as equivariances. Equivariances are common in scientific models, however integrating them directly into expressive inference networks (such as normalizing flows) is not straightforward. We here describe an alternative method to incorporate equivariances under joint transformations of parameters and data. Our method -- called group equivariant neural posterior estimation (GNPE) -- is based on self-consistently standardizing the "pose" of the data while estimating the posterior over parameters. It is architecture-independent, and applies both to exact and approximate equivariances. As a real-world application, we use GNPE for amortized inference of astrophysical binary black hole systems from gravitational-wave observations. We show that GNPE achieves state-of-the-art accuracy while reducing inference times by three orders of magnitude.

13+11 pages, 5+8 figures. [v2]: Minor updates to match published version, code available at https://github.com/dingo-gw/dingo

References in corpus (6)

• Advanced Virgo: a 2nd generation interferometric gravitational wave detector
• A gravitational-wave standard siren measurement of the Hubble constant
• Robust parameter estimation for compact binaries with ground-based gravitational-wave observations using the LALInference software library
• GWTC-2.1: Deep Extended Catalog of Compact Binary Coalescences Observed by LIGO and Virgo During the First Half of the Third Observing Run
• Automatic Posterior Transformation for Likelihood-Free Inference
• A more effective coordinate system for parameter estimation of precessing compact binaries from gravitational waves