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
| Version | Repository | File | Size |
|---|---|---|---|
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 |