Back to Volume
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.
Back to Volume