<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<?xml-stylesheet type="text/xsl" href="/rss.xsl"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>Loss Functions on Abdullah Al Mamun</title>
    <link>https://pwaabdullah.github.io/tags/loss-functions/</link>
    <description>Recent content in Loss Functions on Abdullah Al Mamun</description>
    <image>
      <title>Abdullah Al Mamun</title>
      <url>https://pwaabdullah.github.io/og-default.png</url>
      <link>https://pwaabdullah.github.io/og-default.png</link>
    </image>
    <generator>Hugo</generator>
    <language>en</language>
    <copyright>newabdullah 2025</copyright>
    <lastBuildDate>Wed, 16 Sep 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://pwaabdullah.github.io/tags/loss-functions/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Every Loss Function You Must Know as an ML Engineer</title>
      <link>https://pwaabdullah.github.io/posts/loss-functions-ml-interview/</link>
      <pubDate>Wed, 16 Sep 2026 00:00:00 +0000</pubDate>
      <guid>https://pwaabdullah.github.io/posts/loss-functions-ml-interview/</guid>
      <description>Every loss function worth knowing for an ML interview: cross-entropy, MSE/MAE/Huber, hinge, focal, ranking, contrastive/InfoNCE, KL, and the LLM objectives (SFT, distillation, DPO, RLHF), with the PyTorch API traps and a rapid-fire Q&amp;amp;A.</description>
    </item>
  </channel>
</rss>
