arXiv · 2401.04174
Optimal, fast, and robust inference of reionization-era cosmology with the 21cmPIE-INN
Abstract
Modern machine learning will allow for simulation-based inference from reionization-era 21cm observations at the Square Kilometre Array. Our framework combines a convolutional summary network and a conditional invertible network through a physics-inspired latent representation. It allows for an efficient and extremely fast determination of the posteriors of astrophysical and cosmological parameters, jointly with well-calibrated and on average unbiased summaries. The sensitivity to non-Gaussian information makes our method a promising alternative to the established power spectra.
Explore related subjects
Keep this discovery
Benedikt Schosser, Caroline Heneka, Tilman Plehn. 2024-01-08. Optimal, fast, and robust inference of reionization-era cosmology with the 21cmPIE-INN. https://doi.org/10.21468/scipostphyscore.8.2.037
Cite the original work for its findings. Save a collection to share your selection of sources.