GPTreeO: Dividing Local Gaussian Processes for Online Learning Regression

We implement and extend the Dividing Local Gaussian Process algorithm by Lederer et al. (2020) <doi:10.48550/arXiv.2006.09446>. Its main use case is in online learning where it is used to train a network of local GPs (referred to as tree) by cleverly partitioning the input space. In contrast to a single GP, 'GPTreeO' is able to deal with larger amounts of data. The package includes methods to create the tree and set its parameter, incorporating data points from a data stream as well as making joint predictions based on all relevant local GPs.

Version: 1.0.0
Imports: R6, hash, DiceKriging, mlegp
Suggests: knitr, rmarkdown, spelling, testthat
Published: 2024-09-23
DOI: 10.32614/CRAN.package.GPTreeO
Author: Timo Braun [aut, cre], Anders Kvellestad ORCID iD [aut], Riccardo De Bin ORCID iD [ctb]
Maintainer: Timo Braun <gptreeo.timo.braun at gmail.com>
License: MIT + file LICENSE
NeedsCompilation: no
Language: en-US
Materials: NEWS
CRAN checks: GPTreeO results

Documentation:

Reference manual: GPTreeO.pdf
Vignettes: GPTreeO-Vignette (source, R code)

Downloads:

Package source: GPTreeO_1.0.0.tar.gz
Windows binaries: r-devel: GPTreeO_1.0.0.zip, r-release: GPTreeO_1.0.0.zip, r-oldrel: GPTreeO_1.0.0.zip
macOS binaries: r-release (arm64): GPTreeO_1.0.0.tgz, r-oldrel (arm64): GPTreeO_1.0.0.tgz, r-release (x86_64): GPTreeO_1.0.0.tgz, r-oldrel (x86_64): GPTreeO_1.0.0.tgz

Linking:

Please use the canonical form https://CRAN.R-project.org/package=GPTreeO to link to this page.