gslnls: GSL Nonlinear Least-Squares Fitting

An R interface to nonlinear least-squares optimization with the GNU Scientific Library (GSL), see M. Galassi et al. (2009, ISBN:0954612078). The available trust region methods include the Levenberg-Marquadt algorithm with and without geodesic acceleration, the Steihaug-Toint conjugate gradient algorithm for large systems and several variants of Powell's dogleg algorithm. Bindings are provided to tune a number of parameters affecting the low-level aspects of the trust region algorithms. The interface mimics R's nls() function and returns model objects inheriting from the same class.

Version: 1.1.0
Depends: R (≥ 3.5)
Imports: stats, Matrix
Published: 2021-11-26
Author: Joris Chau [aut, cre]
Maintainer: Joris Chau <joris.chau at openanalytics.eu>
BugReports: https://github.com/JorisChau/gslnls/issues
License: GPL-3
URL: https://github.com/JorisChau/gslnls
NeedsCompilation: yes
SystemRequirements: GSL (>= 2.2)
Language: en-US
Materials: NEWS
In views: Optimization
CRAN checks: gslnls results

Documentation:

Reference manual: gslnls.pdf

Downloads:

Package source: gslnls_1.1.0.tar.gz
Windows binaries: r-devel: gslnls_1.1.0.zip, r-devel-UCRT: gslnls_1.1.0.zip, r-release: gslnls_1.1.0.zip, r-oldrel: gslnls_1.1.0.zip
macOS binaries: r-release (arm64): gslnls_1.1.0.tgz, r-release (x86_64): gslnls_1.1.0.tgz, r-oldrel: gslnls_1.1.0.tgz
Old sources: gslnls archive

Linking:

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