<?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>信息几何 on s-ai-unix's Blog</title><link>https://s-ai-unix.github.io/tags/%E4%BF%A1%E6%81%AF%E5%87%A0%E4%BD%95/</link><description>Recent content in 信息几何 on s-ai-unix's Blog</description><generator>Hugo -- 0.161.1</generator><language>zh-cn</language><lastBuildDate>Tue, 03 Feb 2026 08:23:00 +0800</lastBuildDate><atom:link href="https://s-ai-unix.github.io/tags/%E4%BF%A1%E6%81%AF%E5%87%A0%E4%BD%95/index.xml" rel="self" type="application/rss+xml"/><item><title>数理统计重要定理系列：Fisher信息矩阵的几何、统计与应用</title><link>https://s-ai-unix.github.io/posts/2026-02-03-fisher-information-matrix/</link><pubDate>Tue, 03 Feb 2026 08:23:00 +0800</pubDate><guid>https://s-ai-unix.github.io/posts/2026-02-03-fisher-information-matrix/</guid><description>系统综述Fisher信息矩阵的历史背景、数学推导、几何解释及其在统计推断、机器学习中的深刻应用</description></item><item><title>信息几何：在概率空间中寻找最短路径</title><link>https://s-ai-unix.github.io/posts/2026-01-25-information-geometry/</link><pubDate>Sun, 25 Jan 2026 15:00:00 +0800</pubDate><guid>https://s-ai-unix.github.io/posts/2026-01-25-information-geometry/</guid><description>从 Fisher 信息度量到自然梯度，从黎曼流形到 Wasserstein 距离：全面介绍信息几何这一连接统计学、微分几何与深度学习的交叉领域</description></item></channel></rss>