Post-hoc signal-to-noise and signal-plus-noise pruning with a short resampling run can shrink MCMC-trained Bayesian neural networks by 75% with modest accuracy loss, though uncertainty retention is not measured.
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
-
Compact Bayesian Neural Networks via pruned MCMC sampling
Post-hoc signal-to-noise and signal-plus-noise pruning with a short resampling run can shrink MCMC-trained Bayesian neural networks by 75% with modest accuracy loss, though uncertainty retention is not measured.