REVIEW 3 cited by
Multiplicative Normalizing Flows for Variational Bayesian Neural Networks
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
We reinterpret multiplicative noise in neural networks as auxiliary random variables that augment the approximate posterior in a variational setting for Bayesian neural networks. We show that through this interpretation it is both efficient and straightforward to improve the approximation by employing normalizing flows while still allowing for local reparametrizations and a tractable lower bound. In experiments we show that with this new approximation we can significantly improve upon classical mean field for Bayesian neural networks on both predictive accuracy as well as predictive uncertainty.
Forward citations
Cited by 3 Pith papers
-
Ensemble Neural Networks (ENN): A gradient-free stochastic method
Neural networks can be trained by the EnRML algorithm using covariance matrices instead of gradients, giving uncertainty estimates and robust small-data performance.
-
Quality of Uncertainty Quantification for Bayesian Neural Network Inference
Empirical comparison of ten BNN inference methods shows test log-likelihood can mislead on uncertainty quality and that posterior-structure innovations do not necessarily yield high-quality approximations.
-
Estimating Photometric Redshifts for Galaxies from the DESI Legacy Imaging Surveys with Bayesian Neural Networks Trained by DESI EDR
A 0.18-billion-galaxy photometric redshift catalogue from DESI Legacy images is produced with Bayesian neural networks, showing strong results for bright (BGS) and red (LRG) galaxy samples but poor results for emissio...
Discussion (0). Continue with ORCID to comment.