Buchumschlag

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...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Hitchcock, James (VerfasserIn) , Hundertmark, Markus (VerfasserIn) , Foreman-Mackey, Daniel (VerfasserIn) , Bachelet, Etienne (VerfasserIn) , Dominik, Martin (VerfasserIn) , Street, Rachel (VerfasserIn) , Tsapras, Yiannis (VerfasserIn)
Dokumenttyp: Article (Journal)
Sprache:Englisch
Veröffentlicht: 21 April 2021
In: Monthly notices of the Royal Astronomical Society
Year: 2021, Jahrgang: 504, Heft: 3, Pages: 3561-3579
ISSN:1365-2966
DOI:10.1093/mnras/stab1114
Online-Zugang:Verlag, lizenzpflichtig, Volltext: https://doi.org/10.1093/mnras/stab1114
Volltext
Verfasserangaben:James A. Hitchcock, Markus Hundertmark, Daniel Foreman-Mackey, Etienne Bachelet, Martin Dominik, Rachel Street and Yiannis Tsapras
Beschreibung
Zusammenfassung: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.
Beschreibung:Gesehen am 04.08.2021
Beschreibung:Online Resource
ISSN:1365-2966
DOI:10.1093/mnras/stab1114

Ähnliche Einträge