PyLightcurve-torch: a transit modelling package for deep learning applications in PyTorch. (arXiv:2011.02030v2 [astro-ph.EP] UPDATED)
<a href="http://arxiv.org/find/astro-ph/1/au:+Morvan_M/0/1/0/all/0/1">Mario Morvan</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Tsiaras_A/0/1/0/all/0/1">Angelos Tsiaras</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Nikolaou_N/0/1/0/all/0/1">Nikolaos Nikolaou</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Waldmann_I/0/1/0/all/0/1">Ingo P. Waldmann</a>

We present a new open source python package, based on PyLightcurve and
PyTorch, tailored for efficient computation and automatic differentiation of
exoplanetary transits. The classes and functions implemented are fully
vectorised, natively GPU-compatible and differentiable with respect to the
stellar and planetary parameters. This makes PyLightcurve-torch suitable for
traditional forward computation of transits, but also extends the range of
possible applications with inference and optimisation algorithms requiring
access to the gradients of the physical model. This endeavour is aimed at
fostering the use of deep learning in exoplanets research, motivated by an ever
increasing amount of stellar light curves data and various incentives for the
improvement of detection and characterisation techniques.

We present a new open source python package, based on PyLightcurve and
PyTorch, tailored for efficient computation and automatic differentiation of
exoplanetary transits. The classes and functions implemented are fully
vectorised, natively GPU-compatible and differentiable with respect to the
stellar and planetary parameters. This makes PyLightcurve-torch suitable for
traditional forward computation of transits, but also extends the range of
possible applications with inference and optimisation algorithms requiring
access to the gradients of the physical model. This endeavour is aimed at
fostering the use of deep learning in exoplanets research, motivated by an ever
increasing amount of stellar light curves data and various incentives for the
improvement of detection and characterisation techniques.

http://arxiv.org/icons/sfx.gif