Skip to content
Sagan

Paper

Muon is Not That Special: Random or Inverted Spectra Work Just as Well

Unreadunread

AI summary

The authors challenge the geometric narrative behind the Muon optimizer by showing that precise geometric structure isn't what drives performance. They introduce Freon (based on Schatten quasi-norms) and Kaon (which replaces singular values with random noise), both matching Muon's performance despite lacking coherent geometry. Their analysis reveals that optimizer performance is controlled by two local quantities — alignment and descent potential — rather than global geometric structure, suggesting Muon succeeds by guaranteeing step-size optimality, not by tracking ideal geometry.

Main takeaways:

  • Freon interpolates between SGD and Muon using Schatten quasi-norms; best GPT-2 parameters lie in the quasi-norm regime, which can't be represented by any unitarily invariant LMO.
  • Kaon replaces singular values with random noise yet matches Muon's performance, proving precise geometry isn't necessary.
  • Optimizer performance is controlled by two local quantities: alignment and descent potential, not global geometric structure.
  • Muon succeeds by guaranteeing step-size optimality around these local quantities, not by tracking ideal global geometry.
  • Both Freon and Kaon retain classical convergence guarantees despite their unusual constructions.