Acceleration of Non-Linear Minimisation with PyTorch

2018/05/18 by Bojan Nikolic, Nikolic, Bojan · 1 voice · 1 citation
Computer Science · Physics and Astronomy · #Computational Physics and Python Applications #Model Reduction and Neural Networks #Neural Networks and Applications #astro-ph.IM #physics.data-an

paper · pdf · doi:10.48550/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.

Cited by

• Non-destructive three-dimensional measurement of hand vein based on self-supervised network

Discussions

• Acceleration of Non-Linear Minimisation with PyTorch (2018) [hn, 3 points, 0 comments]

Related

• A Generalizable Approach to Learning Optimizers
• A reformulation to Embedding a Neural Network in a linear program without integer variables
• Training Neural Networks at Any Scale
• Nonparametric Neural Networks
• Tasks, stability, architecture, and compute: Training more effective\n learned optimizers, and using them to train themselves