Accelerating Statistical Inferences in Astrophysics with Neural Networks and Hamiltonian Monte Carlo
Abstract
We present an approach to accelerate statistical inferences in astrophysics by using a combination of neural networks and Hamiltonian Monte Carlo. The neural networks are used to create high-fidelity surrogates of computationally expensive models, while Hamiltonian Monte Carlo accelerates the inferences by more efficiently exploring the parameter space. We demonstrate the potential of this approach by applying it to a realistic model for the Epoch of Reionization.
Cite
Text
Gonzalez-Hernandez et al. "Accelerating Statistical Inferences in Astrophysics with Neural Networks and Hamiltonian Monte Carlo." ICML 2024 Workshops: AI4Science, 2024.Markdown
[Gonzalez-Hernandez et al. "Accelerating Statistical Inferences in Astrophysics with Neural Networks and Hamiltonian Monte Carlo." ICML 2024 Workshops: AI4Science, 2024.](https://mlanthology.org/icmlw/2024/gonzalezhernandez2024icmlw-accelerating/)BibTeX
@inproceedings{gonzalezhernandez2024icmlw-accelerating,
title = {{Accelerating Statistical Inferences in Astrophysics with Neural Networks and Hamiltonian Monte Carlo}},
author = {Gonzalez-Hernandez, Diego and Wolfson, Molly and Hennawi, Joseph},
booktitle = {ICML 2024 Workshops: AI4Science},
year = {2024},
url = {https://mlanthology.org/icmlw/2024/gonzalezhernandez2024icmlw-accelerating/}
}