English(EN) Beyond the Matrix Sign: Quadratic Spectral Descent

新的二次谱下降法提高了GPT预训练效率

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-10 04:00

研究人员开发了一种名为二次谱下降法（QSD）的新优化方法，该方法改进了用于训练大型语言模型的现有Muon算法。QSD将局部曲率信息纳入优化过程，可以改变最优更新的奇异值和方向。通过使用Kronecker因子统计量近似曲率并采用Frank-Wolfe方法，QSD变得实用。在GPT预训练上的实验表明，与Muon及其变体相比，QSD持续降低了验证损失，并将训练时间缩短了高达8.49%，同时达到了匹配的验证损失。 AI

影响这项新的优化技术可能导致更高效的大型语言模型训练，从而降低计算成本和训练时间。

排序理由该集群包含一篇详细介绍LLM新优化方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 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; 该集群包含一篇详细介绍LLM新优化方法的论文。[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.AI TIER_1 English(EN) · Qiaozhe Zhang, Jun Sun, Yingzhuang Liu · 2026-09-10 04:00

超越矩阵符号：二次谱下降

arXiv:2609.07597v1 Announce Type: cross Abstract: Muon can be interpreted as optimizing a linear local objective over a spectral-norm ball. This gives a matrix-sign update that preserves the singular directions of the gradient and assigns the same magnitude to all active singular…

本文如何被排名

报道来源 [1]

超越矩阵符号：二次谱下降

相关实体

相关话题