Skip to content
Hot eventLive

Spectrally Targeted Muon 优化器论文

1 reports1 sources3 hr ago updated

Get the story

AI overview

2026年10月9日,研究者在 arXiv(Machine Learning Theory)发表 Spectrally Targeted Muon 优化器论文。该方法仅对高于或低于阈值 τ 的奇异值做正交化,通过在平移 Gram 矩阵上运行 Newton-Schulz 迭代隔离相关奇异子空间,无需 SVD,并可在 normalized SGD 与 Muon 之间插值。目前报道仅涉及方法提出,未见实验结果或后续验证。

Generated from reports · updated 3 hr ago

Timeline

Follow the coverage from different angles.

Oct 9, 2026
  1. arXiv · Machine Learning Theory
    Spectrally Targeted Muon 优化器:只对部分奇异值正交化

    研究者提出 Spectrally Targeted Muon 优化器,仅对高于或低于阈值 τ 的奇异值做正交化,通过在平移 Gram 矩阵上运行 Newton-Schulz 迭代隔离相关奇异子空间,无需 SVD,并可在 normalized SGD 与 Muon 之间插值。

Heat trend

Current heat 9·Comparable peak 10(Oct 9)·Comparable change over 24 hours –

02.557.510Oct9Oct9Oct9Oct9

The trend compares only the same participants observed continuously; its range may be smaller than the current heat count. Move or click on the chart to inspect hourly heat; use the left and right arrow keys to switch.