Home | Publications | HF25a

SBIAX: Density-Estimation Simulation-Based Inference in JAX

MCML Authors

Jed Homer

→ Group Daniel Grün
Astrophysics, Cosmology and Artificial Intelligence

Abstract

In a typical Bayesian inference problem, the data likelihood is not known. However, in recent years, machine learning methods for density estimation can allow for inference using an estimator of the data likelihood. This likelihood estimator is fit with neural networks that are trained on simulations to maximise the likelihood of the simulation-parameter pairs - one of the many available tools for Simulation Based Inference (SBI), (Cranmer et al., 2020)...

article HF25a