Improved Depth Estimation of Bayesian Neural Networks
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 6 of its 17 references that are in the map. First posted on arXiv 14 Oct 2024.
Builds on
6 of 17 references.
References · 6
- 2014Adam: A Method for Stochastic Optimizationcited by 37,093
- 2015Weight Uncertainty in Neural Networkscited by 554
- 2015Variational Dropout and the Local Reparameterization Trickcited by 490
- 2020Depth Uncertainty in Neural Networkscited by 57
- 2022Variational Inference for Infinitely Deep Neural Networkscited by 10
- 2022Principled Pruning of Bayesian Neural Networks through Variational Free Energy Minimizationcited by 6
Built on by
Not cited yet.