arcopt: Adaptive Regularization using Cubics for Optimization

Implements cubic regularization methods (ARC) for local optimization problems common in statistics and applied research. Provides robust handling of ill-conditioned, nonconvex, and indefinite Hessian problems with automatic saddle point escape. Supports box constraints; linear equality constraints are planned for a future release.

Version: 0.3.0
Depends: R (≥ 4.1.0)
Imports: Rcpp (≥ 1.0.0), utils
LinkingTo: Rcpp
Suggests: testthat (≥ 3.0.0), knitr, rmarkdown, covr, marqLevAlg, trust
Published: 2026-04-29
DOI: 10.32614/CRAN.package.arcopt (may not be active yet)
Author: Marcus Waldman [aut, cre]
Maintainer: Marcus Waldman <marcus.waldman at cuanschutz.edu>
BugReports: https://github.com/marcus-waldman/arcopt/issues
License: MIT + file LICENSE
URL: https://github.com/marcus-waldman/arcopt
NeedsCompilation: yes
Citation: arcopt citation info
Materials: README, NEWS
CRAN checks: arcopt results

Documentation:

Reference manual: arcopt.html , arcopt.pdf
Vignettes: Getting Started with arcopt (source, R code)
Solver modes: cubic, trust-region fallback, and quasi-Newton polish (source, R code)

Downloads:

Package source: arcopt_0.3.0.tar.gz
Windows binaries: r-devel: not available, r-release: arcopt_0.3.0.zip, r-oldrel: not available
macOS binaries: r-release (arm64): arcopt_0.3.0.tgz, r-oldrel (arm64): arcopt_0.3.0.tgz, r-release (x86_64): not available, r-oldrel (x86_64): not available

Linking:

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