Scalable Bayesian Inference for Detection and Deblending in Astronomical Images
Abstract
We present a new probabilistic method for detecting, deblending, and cataloging astronomical sources called the Bayesian Light Source Separator (BLISS). BLISS is based on deep generative models, which embed neural networks within a Bayesian model. For posterior inference, BLISS uses a new form of variational inference known as Forward Amortized Variational Inference. The BLISS inference routine is fast, requiring a single forward pass of the encoder networks on a GPU once the encoder networks are trained. BLISS can perform fully Bayesian inference on megapixel images in seconds, and produces highly accurate catalogs. BLISS is highly extensible, and has the potential to directly answer downstream scientific questions in addition to producing probabilistic catalogs.
Cite
@article{arxiv.2207.05642,
title = {Scalable Bayesian Inference for Detection and Deblending in Astronomical Images},
author = {Derek Hansen and Ismael Mendoza and Runjing Liu and Ziteng Pang and Zhe Zhao and Camille Avestruz and Jeffrey Regier},
journal= {arXiv preprint arXiv:2207.05642},
year = {2022}
}
Comments
Accepted to the ICML 2022 Workshop on Machine Learning for Astrophysics. 5 pages, 2 figures