<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Reblogs on Anton Lee</title><link>https://tachyonicclock.github.io/reblogs/</link><description>Recent content in Reblogs on Anton Lee</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Wed, 07 May 2025 00:00:00 +0000</lastBuildDate><atom:link href="https://tachyonicclock.github.io/reblogs/index.xml" rel="self" type="application/rss+xml"/><item><title>Reservoir Sampling</title><link>https://tachyonicclock.github.io/reblogs/2025-05-07/</link><pubDate>Wed, 07 May 2025 00:00:00 +0000</pubDate><guid>https://tachyonicclock.github.io/reblogs/2025-05-07/</guid><description>Reservoid sampling lets you sample uniformly from a set when you don&amp;rsquo;t know how big the set is. This has applications in continual learning and data stream processing since we do not know the length of the stream.
SAM WHO writes up a blog post explaing it visually: https://samwho.dev/reservoir-sampling/ .</description></item></channel></rss>