Crandore Hub

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>.

Versions across snapshots

VersionRepositoryFileSize
0.1.0 rolling linux/jammy R-4.5 combss_0.1.0.tar.gz 74.7 KiB
0.1.0 rolling linux/noble R-4.5 combss_0.1.0.tar.gz 74.6 KiB
0.1.0 rolling source/ R- combss_0.1.0.tar.gz 37.1 KiB
0.1.0 latest linux/jammy R-4.5 combss_0.1.0.tar.gz 74.7 KiB
0.1.0 latest linux/noble R-4.5 combss_0.1.0.tar.gz 74.6 KiB
0.1.0 latest source/ R- combss_0.1.0.tar.gz 37.1 KiB
0.1.0 2026-04-23 source/ R- combss_0.1.0.tar.gz 0 B

Dependencies (latest)

Imports

Suggests