geosmooth: Geometric Methods for Nonparametric Regression and Density Estimation

Provides geometric methods for nonparametric regression and density estimation on data represented as coordinate matrices or weighted graphs. Methods include local polynomial smoothing, model-averaged local polynomial smoothing, local polynomial lifting trend filtering, synchronized local polynomial lifting trend filtering, order-2 Gaussian and logistic trend filtering, graph low-pass filtering, and Hessian-energy regression. Methodological references include Gajer and Ravel (2025) "Adaptive Geometric Regression for High-Dimensional Structured Data" <doi:10.48550/arXiv.2511.03817>, Fan and Gijbels (1996, ISBN:9780412983214), Wang et al. (2016) "Trend Filtering on Graphs" <https://www.jmlr.org/papers/v17/15-147.html>, and Kim et al. (2009) "Semi-Supervised Regression Using Hessian Energy" <https://papers.nips.cc/paper/3741-semi-supervised-regression-using-hessian-energy-with-an-application-to-semi-supervised-dimensionality-reduction>.

Version: 0.2.1
Depends: R (≥ 4.1.0)
Imports: dgraphs (≥ 0.4.0), digest, jsonlite, MASS, Matrix, methods, parallel, Rcpp, stats, utils
LinkingTo: Rcpp, dgraphs (≥ 0.4.0)
Suggests: genlasso, grip (≥ 0.3.0), knitr, rmarkdown, splines, testthat (≥ 3.0.0), waldo, withr
Published: 2026-11-12
DOI: 10.32614/CRAN.package.geosmooth
Author: Pawel Gajer [aut, cre], Gael Guennebaud [ctb] (Eigen), Benoit Jacob [ctb] (Eigen), Authors of Eigen [cph] (Authorship and copyright in the included Eigen library), Yixuan Qiu [ctb, cph] (Spectra), Contributors to Spectra [cph] (Copyright in the included Spectra library), Sunil Arya [ctb, cph] (ANN), David M. Mount [ctb, cph] (ANN), University of Maryland [cph] (ANN)
Maintainer: Pawel Gajer <pgajer at gmail.com>
BugReports: https://github.com/pgajer/geosmooth/issues
License: GPL (≥ 3)
Copyright: file inst/COPYRIGHTS
geosmooth copyright details
URL: https://pgajer.github.io/geosmooth/, https://github.com/pgajer/geosmooth
NeedsCompilation: yes
SystemRequirements: GNU make
Language: en-US
Materials: README, NEWS
CRAN checks: geosmooth results

Documentation:

Reference manual: geosmooth.html , geosmooth.pdf
Vignettes: Finding your way around geosmooth (source, R code)
Local simplex charts for binary responses (source, R code)
Order-2 logistic trend filtering: synthetic truth and held-out prediction (source, R code)
PCA and PLS charts: synthetic examples and held-out prediction (source, R code)
Projection pursuit with order-2 trend filtering (source, R code)
Synthetic datasets for geometric smoothing (source, R code)
Observed-data heat fits with numerical cross-checks (source, R code)

Downloads:

Package source: geosmooth_0.2.1.tar.gz
Windows binaries: r-devel: geosmooth_0.1.0.zip, r-release: geosmooth_0.2.0.zip, r-oldrel: geosmooth_0.2.0.zip
macOS binaries: r-release (arm64): geosmooth_0.2.0.tgz, r-oldrel (arm64): geosmooth_0.1.0.tgz, r-release (x86_64): geosmooth_0.2.0.tgz, r-oldrel (x86_64): geosmooth_0.2.0.tgz
Old sources: geosmooth archive

Linking:

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