Published March 15, 2026 | Version v0.3.1
Software Open

dfm/tinygp: The tiniest of Gaussian Process libraries

Authors/Creators

  • 1. Center for Computational Astrophysics, Flatiron Institute, New York, NY, USA
  • 2. Department of Physics and Astronomy, Bishop's University, Canada
  • 3. Indian Institute of Technology Gandhinagar: Gandhinagar, Gujarat, IN
  • 4. Massachusetts Institute of Technology, Probabilistic Computing Project, Cambridge, MA, USA
  • 5. Department of Astronomy and the DiRAC Institute, University of Washington, Seattle, WA, USA
  • 6. SRON Netherlands Institute for Space Research, Leiden, The Netherlands
  • 7. Department of Physics, University of Warwick, Coventry, UK
  • 8. Department of Physics and Astronomy, Aarhus University, DK
  • 9. School of Public Health, Imperial College London, UK
  • 10. Helmholtz-Zentrum Dresden-Rossendorf e.V.

Description

tinygp is an extremely lightweight library for building Gaussian Process (GP) models in Python, built on top of JAX. It has a nice interface, and it's pretty fast. Thanks to JAX, tinygp supports things like GPU acceleration and automatic differentiation. Check out the docs for more info: https://tinygp.readthedocs.io

Files

dfm/tinygp-v0.3.1.zip

Files (214.9 kB)

Name Size Download all
md5:a7560a1b083995f5ca53fbdc860b37b6
214.9 kB Preview Download

Additional details

Related works

Is supplement to
Software: https://github.com/dfm/tinygp/tree/v0.3.1 (URL)

Software

Repository URL
https://github.com/dfm/tinygp