Acceleration of Non-Linear Minimisation with PyTorch
arXiv:1805.07439
Abstract
I show that a software framework intended primarily for training of neural networks, PyTorch, is easily applied to a general function minimisation problem in science. The qualities of PyTorch of ease-of-use and very high efficiency are found to be applicable in this domain and lead to two orders of magnitude improvement in time-to-solution with very small software engineering effort.
5 pages, 2 figures, 2 program listings. Full source code available at: https://github.com/bnikolic/oof/