Improved Depth Estimation of Bayesian Neural Networks
Machine Learning
2024-10-16 v2 Machine Learning
Abstract
This paper proposes improvements over earlier work by Nazareth and Blei (2022) for estimating the depth of Bayesian neural networks. Here, we propose a discrete truncated normal distribution over the network depth to independently learn its mean and variance. Posterior distributions are inferred by minimizing the variational free energy, which balances the model complexity and accuracy. Our method improves test accuracy on the spiral data set and reduces the variance in posterior depth estimates.
Cite
@article{arxiv.2410.10395,
title = {Improved Depth Estimation of Bayesian Neural Networks},
author = {Bart van Erp and Bert de Vries},
journal= {arXiv preprint arXiv:2410.10395},
year = {2024}
}
Comments
NeurIPS 2024 Workshop on Bayesian Decision-making and Uncertainty. Available at https://openreview.net/forum?id=6TLRVdWGzI