GPyReg is a lightweight package for Gaussian process regression in Python. It was developed for use with PyVBMC (a Python package for efficient black-box Bayesian inference) but is usable as a standalone package.
The documentation is currently hosted on github.io.
GPyReg is available via pip
and conda-forge
:
python -m pip install gpyreg
or:
conda install --channel=conda-forge gpyreg
GPyReg requires Python version 3.9 or newer.
If you have trouble doing something with GPyReg, spot bugs or strange behavior, or you simply have some questions, please feel free to:
- Post in the lab's Discussions forum with questions or comments about GPyReg, your problems & applications;
- Open an issue on GitHub;
- Contact the project lead at luigi.acerbi@helsinki.fi, putting 'GPyReg' in the subject of the email.
You can also demonstrate your appreciation for GPyReg in the following ways:
- Star ⭐ the repository on GitHub;
- Subscribe to the lab's newsletter for news and updates (new features, bug fixes, new releases, etc.);
- Follow Luigi Acerbi on Twitter for updates about our other projects;
If you are interested in applications of Gaussian process regression to Bayesian inference and optimization, you may also want to check out PyVBMC for efficient black-box inference, and Bayesian Adaptive Direct Search (BADS), our method for fast Bayesian optimization. BADS is currently available only in MATLAB, but a Python version will be released soon.
GPyReg is released under the terms of the BSD 3-Clause License.
GPyReg was developed by members (past and current) of the Machine and Human Intelligence Lab at the University of Helsinki. Development is being supported by the Academy of Finland Flagship programme: Finnish Center for Artificial Intelligence FCAI.