This is a tutorial on some basic non-asymptotic methods and concepts in random matrix theory. The reader will learn several tools for the analysis of the extreme singular values of random matrices with independent rows or columns. Many of these methods sprung off from the development of geometric functional analysis since the 1970's. They have applications in several fields, most notably in theoretical computer science, statistics and signal processing. A few basic applications are covered in...| papers.cool
在《高阶MuP：更简明但更高明的谱条件缩放》的“近似估计”一节中，我们曾“预支”了一个结论：“一个服从标准正态分布的$n\times m$大小的随机矩阵，它的谱范数大致是$\sqrt{n}+\s...| kexue.fm
在文章《初探muP：超参数的跨模型尺度迁移规律》中，我们基于前向传播、反向传播、损失增量和特征变化的尺度不变性推导了muP（Maximal Update Parametrization）。可能对...| kexue.fm
事实上，除了写博客内容，在这几年里，笔者是花了相当一部分时间来做科学空间的“表面功夫”，为此还专门学了一点php、css和js。虽然不敢说精益求精，但总体来说网站的浏览体验应该比前几年要好得多。...| kexue.fm