Robust Simulation-Based Inference in Cosmology with Bayesian Neural Networks. (arXiv:2207.08435v2 [astro-ph.CO] UPDATED)

Simulation-based inference (SBI) is rapidly establishing itself as a standard
machine learning technique for analyzing data in cosmological surveys. Despite
continual improvements to the quality of density estimation by learned models,
applications of such techniques to real data are entirely reliant on the
generalization power of neural networks far outside the training distribution,
which is mostly unconstrained. Due to the imperfections in scientist-created
simulations, and the large computational expense of generating all possible
parameter combinations, SBI methods in cosmology are …

arxiv astro bayesian cosmology inference networks neural networks simulation