Cover Image

PyTorchDIA: a flexible, GPU-accelerated numerical approach to Difference Image Analysis

We present a GPU-accelerated numerical approach for fast kernel and differential background solutions. The model image proposed in the Bramich Difference Image Analysis (DIA) algorithm is analogous to a very simple convolutional neural network (CNN), with a single convolutional filter (i.e. the kern...

Full description

Saved in:
Bibliographic Details
Main Authors: Hitchcock, James (Author) , Hundertmark, Markus (Author) , Foreman-Mackey, Daniel (Author) , Bachelet, Etienne (Author) , Dominik, Martin (Author) , Street, Rachel (Author) , Tsapras, Yiannis (Author)
Format: Article (Journal)
Language:English
Published: 21 April 2021
In: Monthly notices of the Royal Astronomical Society
Year: 2021, Volume: 504, Issue: 3, Pages: 3561-3579
ISSN:1365-2966
DOI:10.1093/mnras/stab1114
Online Access:Verlag, lizenzpflichtig, Volltext: https://doi.org/10.1093/mnras/stab1114
Get full text
Author Notes:James A. Hitchcock, Markus Hundertmark, Daniel Foreman-Mackey, Etienne Bachelet, Martin Dominik, Rachel Street and Yiannis Tsapras
Description
Summary:We present a GPU-accelerated numerical approach for fast kernel and differential background solutions. The model image proposed in the Bramich Difference Image Analysis (DIA) algorithm is analogous to a very simple convolutional neural network (CNN), with a single convolutional filter (i.e. the kernel) and an added scalar bias (i.e. the differential background). Here, we do not solve for the discrete pixel array in the classical, analytical linear least-squares sense. Instead, by making use of PyTorch tensors (GPU compatible multidimensional matrices) and associated deep learning tools, we solve for the kernel via an inherently massively parallel optimization. By casting the DIA problem as a GPU-accelerated optimization that utilizes automatic differentiation tools, our algorithm is both flexible to the choice of scalar objective function, and can perform DIA on astronomical data sets at least an order of magnitude faster than its classical analogue. More generally, we demonstrate that tools developed for machine learning can be used to address generic data analysis and modelling problems.
Item Description:Gesehen am 04.08.2021
Physical Description:Online Resource
ISSN:1365-2966
DOI:10.1093/mnras/stab1114

Similar Items