2DGBNN compresses Bayesian neural networks by clustering weight means and variances into shared 2D Gaussians, reducing parameter counts by up to 99% on ImageNet-scale models with small accuracy losses.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Stochastic Weight Sharing for Bayesian Neural Networks
2DGBNN compresses Bayesian neural networks by clustering weight means and variances into shared 2D Gaussians, reducing parameter counts by up to 99% on ImageNet-scale models with small accuracy losses.