<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Vector Quantization on Nalar</title>
    <link>https://nalar.dev/tags/vector-quantization/</link>
    <description>Recent content in Vector Quantization on Nalar</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Thu, 24 Sep 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://nalar.dev/tags/vector-quantization/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Codebook Collapse Leaves Vector Quantizers with Unused Entries</title>
      <link>https://nalar.dev/codebook-collapse-leaves-vector-quantizers-with-unused-entries/</link>
      <pubDate>Thu, 24 Sep 2026 00:00:00 +0000</pubDate>
      <guid>https://nalar.dev/codebook-collapse-leaves-vector-quantizers-with-unused-entries/</guid>
      <description>&lt;p&gt;A vector quantizer can expose thousands of codebook entries while repeatedly selecting only a small subset. The configured vocabulary then overstates the discrete capacity that is actually used. This state is often called codebook collapse: some entries receive frequent assignments, while others become inactive or nearly inactive.&lt;/p&gt;&#xA;&lt;p&gt;The failure is not a shortage of parameters by itself. It comes from the interaction between encoder outputs, the assignment rule, and the procedure used to update code vectors. Once assignments concentrate around a subset of entries, unused entries may receive little or no signal that would move them toward regions occupied by encoder outputs.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
