Crandore Hub

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>.

Versions across snapshots

VersionRepositoryFileSize
0.1.4 rolling linux/jammy R-4.5 LBBNN_0.1.4.tar.gz 324.8 KiB
0.1.4 rolling linux/noble R-4.5 LBBNN_0.1.4.tar.gz 324.8 KiB
0.1.4 rolling source/ R- LBBNN_0.1.4.tar.gz 165.1 KiB
0.1.4 latest linux/jammy R-4.5 LBBNN_0.1.4.tar.gz 324.8 KiB
0.1.4 latest linux/noble R-4.5 LBBNN_0.1.4.tar.gz 324.8 KiB
0.1.4 latest source/ R- LBBNN_0.1.4.tar.gz 165.1 KiB
0.1.5 2026-04-26 source/ R- LBBNN_0.1.5.tar.gz 372.0 KiB
0.1.4 2026-04-23 source/ R- LBBNN_0.1.4.tar.gz 165.1 KiB
0.1.4 2026-04-09 windows/windows R-4.5 LBBNN_0.1.4.zip 329.1 KiB

Dependencies (latest)

Imports

Suggests