<?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>Optimization on mu0</title><link>https://mu0.ai/tags/optimization/</link><description>Recent content in Optimization on mu0</description><generator>Hugo -- 0.152.2</generator><language>en-us</language><lastBuildDate>Thu, 30 Jul 2026 09:00:00 +1000</lastBuildDate><atom:link href="https://mu0.ai/tags/optimization/index.xml" rel="self" type="application/rss+xml"/><item><title>Quantile Balancing: Treating MoE Routing as an Optimal Assignment Problem</title><link>https://mu0.ai/posts/quantile-balancing-moe-routing/</link><pubDate>Thu, 30 Jul 2026 09:00:00 +1000</pubDate><guid>https://mu0.ai/posts/quantile-balancing-moe-routing/</guid><description>An English summary of Su Jianlin&amp;rsquo;s derivation of Quantile Balancing — posing MoE load balancing as a constrained assignment problem, and showing that biased Top-k routing falls out of its dual as a set of expert congestion prices.</description></item></channel></rss>