English(EN) Curvature-Conditioned Multiscale Momentum with Sphere Constraints for LLM Pretraining

新的LLM预训练方法加速在平坦方向上的训练

作者 PulseAugur 编辑部 · [1 个来源] · 2026-08-31 04:00

研究人员开发了一种名为“曲率条件化多尺度动量与球面约束”（Curvature-Conditioned Multiscale Momentum with Sphere Constraints）的新方法，以提高大型语言模型（LLM）预训练的效率。该技术解决了由噪声梯度和病态损失景观带来的挑战，这些问题会减缓在损失景观关键平坦方向上的进展。通过采用一种专门针对这些平坦方向的多尺度动量，该方法增强了降噪和曲率适应能力，同时球面约束可防止参数膨胀。实验表明，在使用AdamW和Muon等优化器时，在各种架构和模型大小的LLM预训练中均实现了显著加速。 AI

影响可能降低LLM预训练所需的计算成本和时间，使模型开发更加便捷。

排序理由详细介绍LLM预训练新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 13 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍LLM预训练新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, infra; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Shuchen Zhu, Yuxin Fang, Mingze Wang, Kun Yuan · 2026-08-31 04:00

面向LLM预训练的曲率条件化多尺度动量与球面约束

arXiv:2608.28442v1 Announce Type: new Abstract: Pretraining accounts for a large fraction of the total computational cost in LLM training. However, noise-dominant gradients and the highly ill-conditioned loss landscape bring severe challenges. Although modern adaptive optimizers …

本文如何被排名

报道来源 [1]

面向LLM预训练的曲率条件化多尺度动量与球面约束

相关实体

相关话题