The same Transformer architecture follows different spectral scaling laws under different optimizers, with Muon achieving linear hard-rank scaling on tail representations while AdamW shows weak scaling, even when perplexity is matched.
Scaling laws for gradient descent and sign descent for linear bigram models under zipf’s law
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Same Architecture, Different Capacity: Optimizer-Induced Spectral Scaling Laws
The same Transformer architecture follows different spectral scaling laws under different optimizers, with Muon achieving linear hard-rank scaling on tail representations while AdamW shows weak scaling, even when perplexity is matched.