At tiny scale, MoE transformers lower validation loss versus dense models when active parameters match but raise it when total stored parameters match.
Proceedings of Machine Learning and Systems , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Dense vs Sparse Pretraining at Tiny Scale: Active-Parameter vs Total-Parameter Matching
At tiny scale, MoE transformers lower validation loss versus dense models when active parameters match but raise it when total stored parameters match.