论文概要
研究领域: ML 作者: Wenzhi Zhong, Edward Milsom, Michael Murray 发布时间: 2026-07-28 arXiv: 2607.26001
中文摘要
锐度感知最小化（SAM）旨在通过鼓励对小幅度最坏情况参数扰动的不敏感性来改善泛化。然而，”小”扰动的概念本质上是几何依赖的：虽然现有的SAM变体探索了广泛的选择，但关于哪种几何在实践中最有效的清晰视角仍然难以捉摸。最近关于矩阵感知优化器的工作，特别是Muon优化器，表明尊重隐藏层权重的矩阵结构可以带来强大的实证性能。受此启发，我们在SAM的两个阶段都研究了矩阵感知几何：我们引入了针对矩阵值隐藏层参数的分层谱内扰动，并将其与AdamW/SGDW或Muon的外更新结合。在ImageNet-1K上ViT-Small/16和ResNet-50的实验中，我们发现谱内步骤与Muon外步骤的组合表现始终强劲，在所评估方法中在两个模型上都达到了最佳验证准确率。
原文摘要
Sharpness-Aware Minimization (SAM) aims to improve generalization by encouraging insensitivity to small, worst-case parameter perturbations. However, the notion of a “small” perturbation is inherently geometry-dependent: while existing SAM variants have explored a wide range of choices, a clear perspective on which geometries are most effective in practice remains elusive. Recent work on matrix-aware optimization, particularly the Muon optimizer, suggests that respecting the matrix structure of hidden-layer weights can lead to strong empirical performance. Motivated by this, we study matrix-aware geometry in both stages of SAM: we introduce a layerwise spectral inner perturbation for matrix-valued hidden-layer parameters and combine it with either AdamW/SGDW or Muon in the outer update. Ac…
— 自动采集于 2026-07-30
#论文 #arXiv #ML #小凯