# --------------------------------------------
# CITATION file created with {cffr} R package
# See also: https://docs.ropensci.org/cffr/
# --------------------------------------------
 
cff-version: 1.2.0
message: 'To cite package "LBBNN" in publications use:'
type: software
license: MIT
title: 'LBBNN: Latent Binary Bayesian Neural Networks Using ''torch'''
version: 0.1.5
doi: 10.32614/CRAN.package.LBBNN
abstract: 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) <https://doi.org/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)
  <https://doi.org/10.48550/arXiv.2503.10496>.
authors:
- family-names: Skaaret-Lund
  given-names: Lars
  email: lars.skaaret-lund@nmbu.no
- family-names: Hubin
  given-names: Aliaksandr
  email: aliaksandr.hubin@nmbu.no
- family-names: Høyheim
  given-names: Eirik
  email: eirik.hoyheim@ffi.no
repository: https://larselund.r-universe.dev
commit: ed997359d6668500ad9b560f667dd40eea775bcd
date-released: '2026-04-30'
contact:
- family-names: Skaaret-Lund
  given-names: Lars
  email: lars.skaaret-lund@nmbu.no