Pymanopt: A Python Toolbox for Optimization on Manifolds Using Automatic Differentiation
Abstract
Optimization on manifolds is a class of methods for optimization of an objective function, subject to constraints which are smooth, in the sense that the set of points which satisfy the constraints admits the structure of a differentiable manifold. While many optimization problems are of the described form, technicalities of differential geometry and the laborious calculation of derivatives pose a significant barrier for experimenting with these methods.
Cite
Text
Townsend et al. "Pymanopt: A Python Toolbox for Optimization on Manifolds Using Automatic Differentiation." Journal of Machine Learning Research, 2016.Markdown
[Townsend et al. "Pymanopt: A Python Toolbox for Optimization on Manifolds Using Automatic Differentiation." Journal of Machine Learning Research, 2016.](https://mlanthology.org/jmlr/2016/townsend2016jmlr-pymanopt/)BibTeX
@article{townsend2016jmlr-pymanopt,
title = {{Pymanopt: A Python Toolbox for Optimization on Manifolds Using Automatic Differentiation}},
author = {Townsend, James and Koep, Niklas and Weichwald, Sebastian},
journal = {Journal of Machine Learning Research},
year = {2016},
pages = {1-5},
volume = {17},
url = {https://mlanthology.org/jmlr/2016/townsend2016jmlr-pymanopt/}
}