PyTorchDIA: A flexible, GPU-accelerated numerical approach to Difference Image Analysis
arXiv:2104.13715 · doi:10.1093/mnras/stab1114
Abstract
We present a GPU-accelerated numerical approach for fast kernel and differential background solutions. The model image proposed in the Bramich (2008) difference image analysis 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 multi-dimensional matrices) and associated deep learning tools, we solve for the kernel via an inherently massively parallel optimisation. By casting the Difference Image Analysis (DIA) problem as a GPU-accelerated optimisation which utilises 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.
20 pages, 9 figures; updated references
References in corpus (18)
- An overview of gradient descent optimization algorithms
- LSST: from Science Drivers to Reference Design and Anticipated Data Products
- The Zwicky Transient Facility: System Overview, Performance, and First Results
- Mixed Precision Training
- Difference imaging photometry of blended gravitational microlensing events with a numerical kernel
- Proper image subtraction - optimal transient detection, photometry and hypothesis testing
- A New Algorithm For Difference Image Analysis
- Difference Image Analysis: Extension to a Spatially Varying Photometric Scale Factor and Other Considerations
- The Two-Colour EMCCD Instrument for the Danish 1.54m Telescope and SONG
- CCD time-series photometry of the globular cluster NGC 6981: Variable star census and physical parameter estimates
- Effective Image Differencing with ConvNets for Real-time Transient Hunting
- Variable stars in the globular cluster NGC 7492. New discoveries and physical parameters determination
- High Frame-rate Imaging Based Photometry, Photometric Reduction of Data from Electron-multiplying Charge Coupled Devices (EMCCDs)
- Constraining the parameters of globular cluster NGC 1904 from its variable star population
- Regularization Techniques for PSF-Matching Kernels. I. Choice of Kernel Basis
- Difference image analysis: The interplay between the photometric scale factor and systematic photometric errors
- Difference image analysis: Automatic kernel design using information criteria
- ROME/REA: A gravitational microlensing search for exo-planets beyond the snow-line on a global network of robotic telescopes