{
  "id": 16834704,
  "title": "MuonGS: Pretraining LLMs with Relaxed Weight-Norm Control",
  "url": "https://urgent.news/2026/10/27/muongs-pretraining-llms-with-relaxed-weight-norm-control",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-27T17:56:40.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2610.37647v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Weight decay and explicit weight-norm constraints improve optimizer performance in language model pretraining, yet a unified understanding of why such control helps and how much is needed remains incomplete. We analyze norm control in Muon over the entire training trajectory using the \\emph{accumulated effective learning rate}, $C_T=\\sum_{t<T}η_t/\\|W_t\\|_F$, where $η_t$ is the nominal learning…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}