Calibrated NQE enables unbiased field-level cosmological inference from 2D density maps by training mostly on approximate PM simulations and calibrating with ~100 PP simulations.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
astro-ph.CO 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Simulation-based inference uses neural networks trained on simulations to enable parameter inference in cosmology and astrophysics where traditional likelihood calculations are intractable.
citing papers explorer
-
Cosmological Analysis with Calibrated Neural Quantile Estimation and Approximate Simulators
Calibrated NQE enables unbiased field-level cosmological inference from 2D density maps by training mostly on approximate PM simulations and calibrating with ~100 PP simulations.
-
Machine Learning Techniques for Astrophysics and Cosmology: Simulation-Based Inference
Simulation-based inference uses neural networks trained on simulations to enable parameter inference in cosmology and astrophysics where traditional likelihood calculations are intractable.