For single-hidden-layer ReLU Bayesian neural networks, mean-field Gaussian and Monte Carlo dropout posteriors provably cannot express higher predictive variance between well-separated low-variance regions, and this limitation persists empirically in deep networks despite a universality theorem.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
stat.ML 1years
2019 1verdicts
ACCEPT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
On the Expressiveness of Approximate Inference in Bayesian Neural Networks
For single-hidden-layer ReLU Bayesian neural networks, mean-field Gaussian and Monte Carlo dropout posteriors provably cannot express higher predictive variance between well-separated low-variance regions, and this limitation persists empirically in deep networks despite a universality theorem.