PulseAugur
中
实时 10:26:48
English(EN) From SGD to Muon: Adaptive Optimization via Schatten-p Norms

新型优化器可自适应调整深度神经网络训练几何结构

研究人员开发了一种新颖的深度神经网络优化方法,通过动态选择自适应更新几何结构来实现。该方法源自梯度和激活统计数据,可以在标准SGD和更高级的优化器(如Muon)之间进行插值。通过集成逐参数预处理,该框架还可以恢复Adam和MuAdam等特定优化器。这种数据驱动的优化器在运行时开销仅略微增加的情况下,表现出与现有方法相当或更优的性能。 AI

影响 引入了一种新颖的自适应优化技术,有望提高深度学习模型的训练效率和性能。

排序理由 学术论文,详细介绍了一种用于深度神经网络的新型优化方法。[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 →

新型优化器可自适应调整深度神经网络训练几何结构

本文如何被排名

Signal score
11 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
学术论文,详细介绍了一种用于深度神经网络的新型优化方法。[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]

  1. arXiv cs.AI TIER_1 English(EN) · Thomas Massena (DTIPG - SNCF, IRIT), Corentin Friedrich (IRIT), Mathieu Serrurier (IRIT) ·

    从SGD到Muon:通过Schatten-p范数实现自适应优化

    arXiv:2605.19781v2 Announce Type: replace Abstract: Modern optimizers, like Muon, impose matrix-wise geometry constraints on their updates. These matrix-wise constraints can be unified under Linear Minimization Oracle (LMO) theory. However, all current methods impose fixed LMO ge…