{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/geomstats-a-python-package-for-riemannian","title":"geomstats: a Python Package for Riemannian Geometry in Machine Learning","arxiv_id":"1805.08308","date":"2018-05-21","proceeding":"ICLR 2019 5","authors":["Nina Miolane","Johan Mathe","Claire Donnat","Mikael Jorda","Xavier Pennec"],"abstract":"We introduce geomstats, a python package that performs computations on\nmanifolds such as hyperspheres, hyperbolic spaces, spaces of symmetric positive\ndefinite matrices and Lie groups of transformations. We provide efficient and\nextensively unit-tested implementations of these manifolds, together with\nuseful Riemannian metrics and associated Exponential and Logarithm maps. The\ncorresponding geodesic distances provide a range of intuitive choices of\nMachine Learning loss functions. We also give the corresponding Riemannian\ngradients. The operations implemented in geomstats are available with different\ncomputing backends such as numpy, tensorflow and keras. We have enabled GPU\nimplementation and integrated geomstats manifold computations into keras deep\nlearning framework. This paper also presents a review of manifolds in machine\nlearning and an overview of the geomstats package with examples demonstrating\nits use for efficient and user-friendly Riemannian geometry.","url_abs":"http://arxiv.org/abs/1805.08308v2","url_pdf":"http://arxiv.org/pdf/1805.08308v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"geomstats-a-python-package-for-riemannian","repo_url":"https://github.com/geomstats/geomstats","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"geomstats-a-python-package-for-riemannian","repo_url":"https://github.com/ninamiolane/geomstats","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"riemannian-optimization","task_name":"Riemannian optimization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.08308","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}