https://github.com/dfm/tinygp

The tiniest of Gaussian Process libraries
https://github.com/dfm/tinygp

Last synced: 2 days ago
JSON representation

The tiniest of Gaussian Process libraries

• Host: GitHub
• URL: https://github.com/dfm/tinygp
• Owner: dfm
• License: mit
• Created: 2021-02-14T15:51:26.000Z (about 4 years ago)
• Default Branch: main
• Last Pushed: 2025-03-16T16:59:09.000Z (about 1 month ago)
• Last Synced: 2025-04-07T03:09:18.463Z (10 days ago)
• Language: Python
• Homepage: https://tinygp.readthedocs.io
• Size: 1.14 MB
• Stars: 306
• Watchers: 9
• Forks: 25
• Open Issues: 22
• Metadata Files:
  • Readme: README.md
  • Changelog: news/.gitignore
  • Contributing: CONTRIBUTING.md
  • License: LICENSE
  • Code of conduct: CODE_OF_CONDUCT.md

Awesome Lists containing this project

• awesome-jax - tinygp - The _tiniest_ of Gaussian process libraries in JAX. <img src="https://img.shields.io/github/stars/dfm/tinygp?style=social" align="center"> (Libraries / New Libraries)
• awesome-jax - tinygp - The tiniest of Gaussian Process libraries. <img src="https://img.shields.io/github/stars/dfm/tinygp?style=social" align="center"> (Libraries)
• awesome-jax - tinygp - The tiniest of Gaussian Process libraries. <img src="https://img.shields.io/github/stars/dfm/tinygp?style=social" align="center"> (Libraries)

README

        


  


  tinygp


  the tiniest of Gaussian Process libraries

  


  


  

    

  

  

    

  

  

    

  



`tinygp` is an extremely lightweight library for building Gaussian Process (GP)

models in Python, built on top of [`jax`](https://github.com/google/jax). It has

a [nice interface][api-ref], and it's [pretty fast][benchmarks]. Thanks to

`jax`, `tinygp` supports things like GPU acceleration and automatic

differentiation.

Check out the docs for more info: [tinygp.readthedocs.io][docs]

[api-ref]: https://tinygp.readthedocs.io/en/latest/api/index.html

[benchmarks]: https://tinygp.readthedocs.io/en/latest/benchmarks.html

[docs]: https://tinygp.readthedocs.io