<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Stochastic Methods on Chen Kai Blog</title><link>https://www.chenk.top/zh/tags/stochastic-methods/</link><description>Recent content in Stochastic Methods on Chen Kai Blog</description><generator>Hugo</generator><language>zh-CN</language><lastBuildDate>Tue, 27 Sep 2022 09:00:00 +0000</lastBuildDate><atom:link href="https://www.chenk.top/zh/tags/stochastic-methods/index.xml" rel="self" type="application/rss+xml"/><item><title>优化理论（十）：随机优化与方差缩减</title><link>https://www.chenk.top/zh/optimization-theory/10-stochastic-variance-reduction/</link><pubDate>Tue, 27 Sep 2022 09:00:00 +0000</pubDate><guid>https://www.chenk.top/zh/optimization-theory/10-stochastic-variance-reduction/</guid><description>&lt;p>随机梯度下降（SGD）每步只采样单个分量梯度，计算代价远低于全梯度方法——但噪声的代价是什么？能否在保持随机采样优势的同时获得确定性方法的快速收敛？本文从「噪声预算」视角出发，量化这一权衡，并推导解决方案。&lt;/p></description></item></channel></rss>