PINNferring the Hubble Function with Uncertainties (2403.13899v1)
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.
- Association for Computing Machinery, New York, NY, USA, 2005. https://doi.org/10.1145/1102351.1102413.
- Y. Gal, Uncertainty in deep learning, 2016. https://api.semanticscholar.org/CorpusID:86522127.
- 2021. https://api.semanticscholar.org/CorpusID:235593134.
- 2022. https://openreview.net/forum?id=aPOpXlnV1T.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.