PulseAugur
中
实时 07:50:05
English(EN) iMuon: Intrinsic Spectral Optimization on Riemannian Matrix Manifolds

iMuon 优化框架用于流形值参数

研究人员推出 iMuon,一种专为机器学习中流形值参数设计的新型优化框架。该方法通过保持各种矩阵流形(包括固定秩、SPD、Stiefel 和 Grassmann)上的对称性和耦合约束,解决了 Muon 等现有优化器的局限性。iMuon 提供闭式更新,并建立与流形维度和条件无关的收敛速率,在 LoRA 微调 LLM、图像分类和子空间学习的实验中证明了其有效性。 AI

影响 引入了一种新颖的优化方法,可以提高 LLM 微调和其他基于流形的学习任务的效率和适用性。

排序理由 该集群包含一篇详细介绍机器学习新优化框架的研究论文。[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 →

iMuon 优化框架用于流形值参数

本文如何被排名

Signal score
27 / 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机器学习新优化框架的研究论文。[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, other
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]

  1. arXiv cs.AI TIER_1 English(EN) · Yibang Li, Bihari Lal Pandey, Ravi Sah, Andi Han, Cyrus Mostajeran, Pratik Jawanpuria, Bamdev Mishra ·

    iMuon:黎曼矩阵流形上的内在谱优化

    arXiv:2605.09238v2 Announce Type: replace-cross Abstract: Muon and related norm-constrained optimizers, now central to large-scale learning, compute updates via a linear maximization oracle (LMO) over a matrix-norm ball in Euclidean space. However, they do not generalize cleanly …