EnergyCal: Taming Loss Spikes in Muon-Family Optimizers for Sparse MoE Training
Lightweight rule that tames loss spikes from Muon-family optimizers in sparse MoE training.
Explainer · on the wire
The explainer for this story is still on the wire.
The claim, the mechanism, and the figures land here once generated.
Source · arXiv wire
arxiv.org/abs/2610.37062cs.LG · cs.AI · cs.CL