<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Error Recursion on Yuchen Du</title><link>https://dudusoar.github.io/tags/error-recursion/</link><description>Recent content in Error Recursion on Yuchen Du</description><generator>Hugo -- 0.164.0</generator><language>en-us</language><lastBuildDate>Fri, 17 Jul 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://dudusoar.github.io/tags/error-recursion/index.xml" rel="self" type="application/rss+xml"/><item><title>Model Error as Distance to the True Target</title><link>https://dudusoar.github.io/posts/stochastic-approximation/02-model-error-as-distance-to-target/</link><pubDate>Fri, 17 Jul 2026 00:00:00 +0000</pubDate><guid>https://dudusoar.github.io/posts/stochastic-approximation/02-model-error-as-distance-to-target/</guid><description>Why convergence should track distance to the true target rather than the size of the latest update.</description></item><item><title>Expand the Error into Initial Bias and Historical Noise</title><link>https://dudusoar.github.io/posts/stochastic-approximation/18-expanding-the-error-recursion/</link><pubDate>Fri, 17 Jul 2026 00:00:00 +0000</pubDate><guid>https://dudusoar.github.io/posts/stochastic-approximation/18-expanding-the-error-recursion/</guid><description>The explicit error formula separates the residual initial condition from the weighted sum of all past disturbances.</description></item></channel></rss>