# Sampling-free Variational Inference for Neural Networks with Multiplicative Activation Noise

Source: [Sampling-free Variational Inference for Neural Networks with Multiplicative Activation Noise](<https://www.sota2.com/research/paper/68fa698e1e209131cea22927>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:02:46.333Z

Authors: Jannik Schmitt, Stefan Roth

Published: 2021-03-15T16:16:18.000Z

## Abstract

To adopt neural networks in safety critical domains, knowing whether we can trust their predictions is crucial. Bayesian neural networks (BNNs) provide uncertainty estimates by averaging predictions with respect to the posterior weight distribution. Variational inference methods for BNNs approximate the intractable weight posterior with a tractable distribution, yet mostly rely on sampling from the variational distribution during training and inference. Recent sampling-free approaches offer an alternative, but incur a significant parameter overhead. We here propose a more efficient parameterization of the posterior approximation for sampling-free variational inference that relies on the distribution induced by multiplicative Gaussian activation noise. This allows us to combine parameter efficiency with the benefits of sampling-free variational inference. Our approach yields competitive results for standard regression problems and scales well to large-scale image classification tasks including ImageNet.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2103.08497>)

[PDF](<https://arxiv.org/pdf/2103.08497.pdf>)