Dynamic sparse training of multiple heads on a shared backbone outperforms full dense ensembles on ImageNet and C4 while using less compute.
Title resolution pending
1 Pith paper cite this work, alongside 121 external citations. Polarity classification is still indexing.
1
Pith paper citing it
121
external citations · OpenAlex
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
NeuroTrails: Training with Dynamic Sparse Heads as the Key to Effective Ensembling
Dynamic sparse training of multiple heads on a shared backbone outperforms full dense ensembles on ImageNet and C4 while using less compute.