Technology & AIJul 31, 2026
Sign compression for Muon: SignMuon, MuonSign, and the Limits of Error Feedback
SignMuon compresses the Muon update to one bit per parameter by taking its elementwise sign, providing the most direct way to run a matrix-aware optimizer under an extremely low communication budget.
SignMuon compresses the Muon update to one bit per parameter by taking its elementwise sign, providing the most direct way to run a matrix-aware optimizer under an extremely low communication budget. It outperforms SignSGD in practice, yet it can ascend even on a linear…
Sign in to learn & save →
The frontier is open to all. Sign in to learn this from first principles and save it to your knowledge base.