combss: Continuous Optimisation Towards Best Subset Selection
Best subset selection in generalised linear models via continuous optimisation. Reformulates the NP-hard discrete subset selection problem as a continuous optimisation over the hypercube [0,1]^p, solved via a Frank-Wolfe homotopy algorithm with closed-form ridge inner solves. Supports linear (Gaussian), binary logistic, and multinomial regression. For methodological details see Moka, Liquet, Zhu and Muller (2024) <doi:10.1007/s11222-024-10387-8> and Mathur, Liquet, Muller and Moka (2026) <doi:10.48550/arXiv.2603.21952>.
| Version: | 0.1.0 |
| Imports: | glmnet (≥ 4.0), stats |
| Suggests: | testthat (≥ 3.0.0), knitr, rmarkdown |
| Published: | 2026-05-11 |
| DOI: | 10.32614/CRAN.package.combss |
| Author: | Benoit Liquet 
[aut, cre],
Anant Mathur [aut],
Sarat Moka [aut] |
| Maintainer: | Benoit Liquet <benoit.liquet at univ-pau.fr> |
| License: | GPL-3 |
| URL: | https://github.com/benoit-liquet/combss |
| NeedsCompilation: | no |
| CRAN checks: | combss results |
Documentation:
| Reference manual: | combss.html , combss.pdf |
| Vignettes: |
Best subset selection with combss (source, R code) |
Downloads:
| Package source: | combss_0.1.0.tar.gz |
| Windows binaries: | r-devel: combss_0.1.0.zip, r-release: combss_0.1.0.zip, r-oldrel: combss_0.1.0.zip |
| macOS binaries: | r-release (arm64): combss_0.1.0.tgz, r-oldrel (arm64): combss_0.1.0.tgz, r-release (x86_64): combss_0.1.0.tgz, r-oldrel (x86_64): combss_0.1.0.tgz |
Linking:
Please use the canonical form https://CRAN.R-project.org/package=combss to link to this page.