English(EN) Pretraining Data Scale Reverses the Muon-AdamW Fine-Tuning Gap

在大型数据集的 LLM 微调中，AdamW 优于 Muon 优化器

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-02 18:56

一篇新论文研究了 Muon 优化器与 AdamW 在大型语言模型预训练中的性能比较。虽然 Muon 最初显示出速度优势，但研究表明，在微调后，尤其是在更大的预训练数据集下，AdamW 的表现优于 Muon。这种逆转可以用边际传播比来解释，该比率表明随着数据预算的增加，AdamW 的效率会更高。 AI

影响表明 AdamW 可能是比 Muon 更稳健的 LLM 微调选择，尤其是在拥有大量预训练数据的情况下。

排序理由研究论文，分析了优化器在 LLM 预训练和微调中的性能。[lever_c_demoted from research: ic=1 ai=1.0]

在 Hugging Face Daily Papers 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: 2 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 研究论文，分析了优化器在 LLM 预训练和微调中的性能。[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: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

Hugging Face Daily Papers TIER_1 English(EN) · 2026-11-02 18:56

Pretraining Data Scale Reverses the Muon-AdamW Fine-Tuning Gap

Muon has recently emerged as a promising optimizer for pretraining large language models, offering a speedup over AdamW in minimizing pretraining loss. However, it remains unclear whether Muon's advantage persists after fine-tuning. In this paper, we study the downstream behavior…

本文如何被排名

报道来源 [1]

Pretraining Data Scale Reverses the Muon-AdamW Fine-Tuning Gap

相关实体

相关话题