English

PINNferring the Hubble Function with Uncertainties

Cosmology and Nongalactic Astrophysics 2024-03-25 v1 Instrumentation and Methods for Astrophysics High Energy Physics - Phenomenology

Abstract

The Hubble function characterizes a given Friedmann-Robertson-Walker spacetime and can be related to the densities of the cosmological fluids and their equations of state. We show how physics-informed neural networks (PINNs) emulate this dynamical system and provide fast predictions of the luminosity distance for a given choice of densities and equations of state, as needed for the analysis of supernova data. We use this emulator to perform a model-independent and parameter-free reconstruction of the Hubble function on the basis of supernova data. As part of this study, we develop and validate an uncertainty treatment for PINNs using a heteroscedastic loss and repulsive ensembles.

Keywords

Cite

@article{arxiv.2403.13899,
  title  = {PINNferring the Hubble Function with Uncertainties},
  author = {Lennart Röver and Björn Malte Schäfer and Tilman Plehn},
  journal= {arXiv preprint arXiv:2403.13899},
  year   = {2024}
}

Comments

21 pages, 12 figures

R2 v1 2026-06-28T15:27:51.677Z