DEN is a shared-trunk multi-branch ensemble that reports roughly 4-6x faster inference than standard ensembles on simple benchmarks, with similar accuracy.
Handling estimation uncertainty with bootstrapping: Empirical evaluation in the context of hybrid prediction methods
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
cs.LG 1years
2024 1verdicts
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Divergent Ensemble Networks: Enhancing Uncertainty Estimation with Shared Representations and Independent Branching
DEN is a shared-trunk multi-branch ensemble that reports roughly 4-6x faster inference than standard ensembles on simple benchmarks, with similar accuracy.