Celeste: Variational Inference for a Generative Model of Astronomical Images
Abstract
We present a new, fully generative model of optical telescope image sets, along with a variational procedure for inference. Each pixel intensity is treated as a Poisson random variable, with a rate parameter dependent on latent properties of stars and galaxies. Key latent properties are themselves random, with scientific prior distributions constructed from large ancillary data sets. We check our approach on synthetic images. We also run it on images from a major sky survey, where it exceeds the performance of the current state-of-the-art method for locating celestial bodies and measuring their colors.
Cite
Text
Regier et al. "Celeste: Variational Inference for a Generative Model of Astronomical Images." International Conference on Machine Learning, 2015.Markdown
[Regier et al. "Celeste: Variational Inference for a Generative Model of Astronomical Images." International Conference on Machine Learning, 2015.](https://mlanthology.org/icml/2015/regier2015icml-celeste/)BibTeX
@inproceedings{regier2015icml-celeste,
title = {{Celeste: Variational Inference for a Generative Model of Astronomical Images}},
author = {Regier, Jeffrey and Miller, Andrew and McAuliffe, Jon and Adams, Ryan and Hoffman, Matt and Lang, Dustin and Schlegel, David and Prabhat, Mr},
booktitle = {International Conference on Machine Learning},
year = {2015},
pages = {2095-2103},
volume = {37},
url = {https://mlanthology.org/icml/2015/regier2015icml-celeste/}
}