Paper:	Acceleration of Non-Linear Minimization with PyTorch
Volume:	523, Astronomical Data Analysis Software and Systems XXVIII
Page:	63
Authors:	Nikolic, B.
Abstract:	Minimization (or, equivalently, maximization) of non-linear functions is a widespread tool in astronomy, e.g., maximum likelihood or maximum a-posteriori estimates of model parameters. Training of machine learning models can also be expressed as a minimization problem (although with some idiosyncrasies). This similarity opens the possibility of re-purposing machine learning software for general minimization problems in science. I show that PyTorch, a software framework intended primarily for training of neural networks, can easily be applied to general function minimization in science. I demonstrate this with an example inverse problem, the Out-of-Focus Holography technique for measuring telescope surfaces, where a improvement in time-to-solution of around 300 times is achieved with respect to a conventional NumPy implementation. The software engineering effort needed to achieve this speed is modest, and readability and maintainability are largely unaffected.

Astronomical Society of the Pacific
Conference Series

© Copyright 1988 - 2024 - Astronomical Society of the Pacific
No part of the material protected by this copyright may be reproduced or used in any form other than for personal use without written permission from the ASP.

Page generated in 0.043 seconds