Improved Depth Estimation of Bayesian Neural Networks
This work addresses depth estimation in Bayesian neural networks, which is an incremental improvement over prior methods.
The paper tackles the problem of estimating the depth of Bayesian neural networks by proposing a discrete truncated normal distribution to independently learn mean and variance, resulting in improved test accuracy on the spiral data set and reduced variance in posterior depth estimates.
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.