On Mamba-2 130M, Muon on the output projection alone gives lower validation loss and better token efficiency than Muon on the input projection or on both, across corpora and budgets.
Transformers are SSMs: Generalized models and efficient algorithms through structured state space duality,
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
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Muon Meets Mamba: Spectral Optimization for State Space Models
On Mamba-2 130M, Muon on the output projection alone gives lower validation loss and better token efficiency than Muon on the input projection or on both, across corpora and budgets.