<?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>Postulate on SciDraft | A Hugo Theme</title><link>https://www.zhumengyao.com/scidraft/tags/postulate/</link><description>Recent content in Postulate on SciDraft | A Hugo Theme</description><generator>Hugo</generator><language>en</language><lastBuildDate>Mon, 21 Sep 2026 12:32:00 +0900</lastBuildDate><atom:link href="https://www.zhumengyao.com/scidraft/tags/postulate/index.xml" rel="self" type="application/rss+xml"/><item><title>Smoothness of the Loss (postulate)</title><link>https://www.zhumengyao.com/scidraft/notes/demo-note-postulate-smoothness/</link><pubDate>Mon, 21 Sep 2026 12:32:00 +0900</pubDate><guid>https://www.zhumengyao.com/scidraft/notes/demo-note-postulate-smoothness/</guid><description>&lt;p&gt;&lt;strong&gt;Demo note.&lt;/strong&gt; This note demonstrates what the &lt;strong&gt;SciDraft&lt;/strong&gt; Hugo theme can do
for academic and scientific publishing — for research institutions, researchers
and students. Its content is demonstration material only: readers should ignore
whether the demo content is correct.&lt;/p&gt;
&lt;p&gt;Step sizes in deep learning are chosen as if the loss were smooth in its parameters, and
that is an assumption, not a theorem. It is the smoothness postulate: the gradient does
not change arbitrarily fast, so a small step in parameter space produces a predictable
change in loss.&lt;/p&gt;</description></item></channel></rss>