One Simple Trick to Fix Your Bayesian Neural Network
Machine Learning
2022-07-28 v1 Machine Learning
Abstract
One of the most popular estimation methods in Bayesian neural networks (BNN) is mean-field variational inference (MFVI). In this work, we show that neural networks with ReLU activation function induce posteriors, that are hard to fit with MFVI. We provide a theoretical justification for this phenomenon, study it empirically, and report the results of a series of experiments to investigate the effect of activation function on the calibration of BNNs. We find that using Leaky ReLU activations leads to more Gaussian-like weight posteriors and achieves a lower expected calibration error (ECE) than its ReLU-based counterpart.
Keywords
Cite
@article{arxiv.2207.13167,
title = {One Simple Trick to Fix Your Bayesian Neural Network},
author = {Piotr Tempczyk and Ksawery Smoczyński and Philip Smolenski-Jensen and Marek Cygan},
journal= {arXiv preprint arXiv:2207.13167},
year = {2022}
}