<?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>Mingyuan (William) Zhang on Mingyuan Zhang</title>
    <link>https://mingyuanzhang.com/</link>
    <description>Recent content in Mingyuan (William) Zhang on Mingyuan Zhang</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <atom:link href="https://mingyuanzhang.com/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Publications and Manuscripts</title>
      <link>https://mingyuanzhang.com/publications/</link>
      <pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate>
      <guid>https://mingyuanzhang.com/publications/</guid>
      <description>&lt;p&gt;&lt;strong&gt;Exponential Convex Calibration Dimension for the Multi-Label Jaccard Measure.&lt;/strong&gt;&lt;br&gt;
Mingyuan Zhang.&lt;br&gt;
Preprint, 2026.&lt;br&gt;
[&lt;a href=&#34;https://arxiv.org/abs/2608.13549&#34;&gt;link&lt;/a&gt;]&lt;br&gt;&lt;/p&gt;
&lt;p&gt;&lt;strong&gt;Exact Rank and Convex Calibration Dimension Lower Bounds for the Multi-Label F1 Loss.&lt;/strong&gt;&lt;br&gt;
Mingyuan Zhang.&lt;br&gt;
Preprint, 2026.&lt;br&gt;
[&lt;a href=&#34;https://arxiv.org/abs/2608.08399&#34;&gt;link&lt;/a&gt;]&lt;br&gt;&lt;/p&gt;
&lt;p&gt;&lt;strong&gt;Convex Calibrated Output Coding Surrogates for Low-Rank Loss Matrices, with Applications to Multi-Label Learning.&lt;/strong&gt;&lt;br&gt;
Harish G. Ramaswamy*, Mingyuan Zhang*, Shivani Agarwal, Robert C. Williamson.&lt;br&gt;
In preparation, 2025.&lt;br&gt;&lt;/p&gt;
&lt;p&gt;&lt;strong&gt;STATISTICAL MACHINE LEARNING FOR COMPLEX CLASSIFICATION PROBLEMS.&lt;/strong&gt;&lt;br&gt;
Mingyuan Zhang.&lt;br&gt;
Dissertation, 2024.&lt;br&gt;
[&lt;a href=&#34;https://mingyuanzhang.com/papers/Zhang_upenngdas_0175C_16687.pdf&#34;&gt;pdf&lt;/a&gt;][&lt;a href=&#34;https://repository.upenn.edu/entities/publication/974a28a3-5901-454e-9a74-d64f60f26cd8&#34;&gt;link&lt;/a&gt;]&lt;br&gt;&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
