English(EN) Let's Scale Step by Step: Compute-Efficient Hyperparameter Transfer for Large-Scale Mixture-of-Experts

新框架高效预测大型MoE模型最优学习率

作者 PulseAugur 编辑部 · [1 个来源] · 2026-08-20 13:57

研究人员开发了一种新颖的两步框架，可高效确定大型混合专家（MoE）模型的最优学习率。该方法利用不同模型宽度之间的超参数迁移，并将研究结果外推到海量token预算，显著降低了传统超参数搜索的计算成本。该框架采用了最大更新参数化（Maximal Update Parameterization）的适配和Muon优化器，并成功应用于预训练一个155B参数的基础模型，证明了其在预测大规模MoE训练最优配置方面的有效性。 AI

影响降低了训练大型MoE模型的计算成本，实现了更高效的开发。

排序理由详细介绍大型模型新训练方法的学术论文。[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: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍大型模型新训练方法的学术论文。[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: 20 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 [1]

Hugging Face Daily Papers TIER_1 English(EN) · 2026-08-20 13:57

循序渐进：面向大规模混合专家的计算高效超参数迁移

A two-step hyperparameter transfer framework predicts optimal learning rates for large Mixture-of-Experts models by scaling across widths and token budgets, enabling efficient pretraining without costly sweeps.

本文如何被排名

报道来源 [1]

循序渐进：面向大规模混合专家的计算高效超参数迁移

相关实体

相关话题