PulseAugur
中
实时 11:11:30

新的FOAM优化器以更低的成本实现了SOAP/Muon大语言模型训练性能的匹配

研究人员开发了Factored One-sided Adam-Moment (FOAM),这是一种新的优化器,旨在使SOAP等二阶优化方法在大型语言模型 (LLM) 预训练中更具实用性。FOAM通过减少内存使用和计算开销来实现这一点,具体方法是丢弃输出侧的Kronecker因子并使用因子化的Adam-moment估计器。这种方法使FOAM能够匹配更强的SOAP和Muon基线的性能,同时使用的优化器状态显著减少,运行速度相当。 AI

影响 这项研究通过使更高级的优化技术更易于获得,可能导致更高效、更具成本效益的大型语言模型训练。

排序理由 该集群描述了一篇关于用于大语言模型预训练的新型优化算法的最新研究论文。

在 Hugging Face Daily Papers 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

新的FOAM优化器以更低的成本实现了SOAP/Muon大语言模型训练性能的匹配

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
该集群描述了一篇关于用于大语言模型预训练的新型优化算法的最新研究论文。
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
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
10 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [2]

  1. Hugging Face Daily Papers TIER_1 English(EN) ·

    Factored One-sided Adam-Moment for Practical and Scalable SOAP

    Second-order optimizers (e.g., Shampoo, SOAP) have emerged as compelling alternatives to Adam/AdamW and promise faster per-step convergence than AdamW in transformer training. However, they still remain costly in practice, and even SOAP still pays substantial optimizer-state memo…

  2. Hugging Face Daily Papers TIER_1 English(EN) ·

    面向实际和可扩展SOAP的因子化单边Adam-Moment

    FOAM is a lightweight SOAP variant that uses input-only preconditioning and a factored Adam-moment estimator to match strong second-order and Muon baselines in LLM pre-training while using half the optimizer state and running at Muon-class speed.