std_prior

A function to generate prior standard deviations for
each weight and bias in an LBBNN layer.

internal

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>.

Lars Skaaret-Lund

LBBNN

Latent Binary Bayesian Neural Networks Using 'torch'

Aliaksandr Hubin

Eirik Høyheim

std_prior function

<dl><dt>x</dt>
<dd>A number greater than 0.</dd></dl>

Arguments

Generate prior standard deviation for weights and biases of either linear or convolutional layers. — std_prior

<dl>

<dt>x</dt>
<dd>A number greater than 0.</dd>

</dl>

std_prior: Generate prior standard deviation for weights and biases of either linear or convolutional layers.

Description

Usage

Value

Arguments