The solution on the Elements of Statistical Learning ( Ex. 8)
来源:互联网 发布:淘宝女装网红店有哪些 编辑:程序博客网 时间:2024/06/05 03:46
Preface
If you find any errata or have a good idea, please contact me vi tongust@163.com.
Ex. 8.1
First of all, we should refer to the theory Kullback-Leibler Divergence. Here, I just give a brief derivation.
To proof KL divergence, we use the Jensen Inequality:
The constrains which the formula must satisfy are: the function
In this case, we construct a simple convex function
Substitute
As we know
Therefore, we get the KL divergence:
Since we has shown that (8.61) is maximized as a function of
Ex. 8.2
Off the topics
Since this exercise is based on one paper
Proof
I will use the notations in [1] instead of those in ESL which is a bit confusing to me. (Denote
We want to proof : For a fixed value
From the hint, we use Lagrange Multiplier to rewrite our formula.
To get the stationary points, we set the gradient of
To simplify:
From (4), it follows that
Summing (4) W.R.T
Substitute (7) into (4):
Ex. 8.3
Ex. 8.4
Ex. 8.5
Ex. 8.6
Ex. 8.7
Proof f(x) is non-decreasing under update (8.63)
From (8.62), we have
Proof EM algorithm (Sec. 8.5.2) is an example of an EM algorithms
This exercise need us to show following:
On one hand, from (8.46), we can denote that:
Hence, the left hand side (l.h.s) of equation (2) can be simplified as:
On the other hand, also from (8.46), the r.h.s of (2) can be written as:
From Ex. 8.1, we see:
Finally, we get (4)
Reference
[1] Neal, Radford M., and G. E. Hinton. A view of the EM algorithm that justifies incremental, sparse, and other variants. Learning in Graphical Models. Springer Netherlands, 2000:355-368.
- The solution on the Elements of Statistical Learning ( Ex. 8)
- The Elements of Statistical Learning学习开篇
- The Elements of Statistical Learning第一章翻译
- The Elements of Statistical Learning的笔记
- The Elements of Statistical Learning (第4章)
- ≪统计学习精要(The Elements of Statistical Learning)≫课堂笔记(一)
- ≪统计学习精要(The Elements of Statistical Learning)≫课堂笔记(二)
- ≪统计学习精要(The Elements of Statistical Learning)≫课堂笔记(三)
- ≪统计学习精要(The Elements of Statistical Learning)≫课堂笔记(四)
- The Elements of Statistical Learning 读书总结(持续更新中)
- ≪统计学习精要(The Elements of Statistical Learning)≫课堂笔记(一)
- ≪统计学习精要(The Elements of Statistical Learning)≫课堂笔记(二)
- ≪统计学习精要(The Elements of Statistical Learning)≫课堂笔记(三)
- ≪统计学习精要(The Elements of Statistical Learning)≫课堂笔记(四)
- ≪统计学习精要(The Elements of Statistical Learning)≫课堂笔记(五)
- ≪统计学习精要(The Elements of Statistical Learning)≫课堂笔记(六)
- ≪统计学习精要(The Elements of Statistical Learning)≫课堂笔记(七)
- ≪统计学习精要(The Elements of Statistical Learning)≫课堂笔记(八)
- JDK命令行工具
- 定时器的应用小案例(超酷时钟)
- String类方法示例
- 搜索引擎技术介绍
- 一周乱弹(1,jquery窗口变化触发的方法。2,Intellij出现 java.lang.OutOfMemory)
- The solution on the Elements of Statistical Learning ( Ex. 8)
- Python数据分析|第2章 引言(例子)
- 使用avilib封装MJPEG数据应用实例
- 数组中的逆序对
- 实现字符串翻转(包含中文汉字)
- 161217
- 数据结构之栈的java实现
- 字符数组和字符串总结
- php中json_encode()在ie浏览器下无法生成对应的json串