Scalable Bayesian Inference for Detection and Deblending in Astronomical Images

TL;DR

The paper introduces BLISS, a fast, scalable Bayesian method using deep generative models and forward amortized variational inference for detecting and deblending sources in large astronomical images, enabling rapid, accurate probabilistic catalogs.

Contribution

It presents BLISS, a novel probabilistic framework combining deep generative models with a new variational inference technique for efficient astronomical image analysis.

Findings

BLISS achieves rapid inference on megapixel images in seconds.

BLISS produces highly accurate probabilistic catalogs.

The method is highly extensible for scientific analysis.

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.