LBBNN: Latent Binary Bayesian Neural Networks Using 'torch'
Latent binary Bayesian neural networks (LBBNNs) are implemented using 'torch', an R interface to the LibTorch backend. Supports mean-field variational inference as well as flexible variational posteriors using normalizing flows. The standard LBBNN implementation follows Hubin and Storvik (2024) <doi:10.3390/math12060788>, using the local reparametrization trick as in Skaaret-Lund et al. (2024) <https://openreview.net/pdf?id=d6kqUKzG3V>. Input-skip connections are also supported, as described in Høyheim et al. (2025) <doi:10.48550/arXiv.2503.10496>.
| Version: | 0.1.2 |
| Depends: | R (≥ 3.5) |
| Imports: | ggplot2,torch,igraph,coro,svglite |
| Suggests: | testthat (≥ 3.0.0),knitr,rmarkdown,torchvision |
| Published: | 2025-12-10 |
| DOI: | 10.32614/CRAN.package.LBBNN |
| Author: | Lars Skaaret-Lund [aut, cre], Aliaksandr Hubin [aut], Eirik Høyheim [aut] |
| Maintainer: | Lars Skaaret-Lund <lars.skaaret-lund at nmbu.no> |
| License: | MIT + fileLICENSE |
| NeedsCompilation: | no |
| Language: | en-US |
| Materials: | README,NEWS |
| CRAN checks: | LBBNN results |
Documentation:
Downloads:
Linking:
Please use the canonical formhttps://CRAN.R-project.org/package=LBBNNto link to this page.