GPmp Documentation

GPmp is a lightweight toolkit for Gaussian process modeling. It provides compact building blocks for GP interpolation, regression, parameter selection, diagnostics, posterior parameter sampling, and conditional simulation.

The package favors explicit modeling choices: users provide the mean and covariance functions, while GPmp supplies common covariance kernels, parameter initialization and selection routines, numerical backends, and diagnostic helpers.

Features

  • GP interpolation and regression with known or unknown mean functions.

  • Maximum likelihood, restricted maximum likelihood, REMAP, and custom parameter-selection criteria.

  • Posterior parameter sampling with MH, NUTS, and SMC helpers.

  • Leave-one-out diagnostics, model reports, and selection-criterion plots.

  • Conditional sample paths and utilities for Matérn covariance models.

Positioning

GPmp targets kriging and computer-experiment code where the mean function, covariance function, covariance parameters, selection criterion, diagnostics, and numerical backend objects should remain directly inspectable.

  • GPyTorch, GPflow, and GPJax provide broader automatic-differentiation ecosystems for scalable, variational, deep, or multi-output GP models.

  • SMT focuses on engineering surrogate modeling, with sampling methods, mixed variables, and several surrogate model families.

  • scikit-learn provides a stable estimator API for standard GP regression and classification.

GPmp’s role is narrower: explicit parameter selection and diagnostics for exact GP interpolation and regression, with compact code that can be adapted for research experiments.

Installation from source

Editable installation requires a local clone of the repository. Clone GPmp, enter the repository root, then run pip install -e .:

git clone https://github.com/gpmp-dev/gpmp.git
cd gpmp
pip install -e .

Documentation map

Start with GPmp Tutorial for a complete Hartmann4 example. Use Examples for task-specific scripts and API reference for the API reference.

How to Cite

@software{gpmp2026,
  author       = {Emmanuel Vazquez},
  title        = {GPmp: the Gaussian Process micro package},
  year         = {2026},
  url          = {https://github.com/gpmp-dev/gpmp},
  note         = {Version 0.9.37},
}

Authors

See AUTHORS.md.

License

GPmp is free software released under the GNU General Public License v3.0. See LICENSE.txt for details.