forked from datawhalechina/pumpkin-book
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
西瓜书第8页NFL定理解析
- Loading branch information
Showing
1 changed file
with
8 additions
and
1 deletion.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1 +1,8 @@ | ||
nothing | ||
## 1.2 | ||
|
||
没有免费午餐定理(NFL)定理证明 | ||
|
||
[解析]:这里要说明一下:$L_a$ 表示训练出来的算法,$f$ 是表示真实目标函数。这条定理希望求出的是:某个算法对于某一类问题下所有真实目标函数的误差总和。书中给出的是简化版证明,仅考虑二分类问题。理解的难点在于第二个等号到第三个等号之间的转化。在二分类问题下,真实目标可以是任意一个将 |X|个样本映射到 {0,1} 的函数,一共有 $2^{|X|}$ 个 $f$,而且每一个 $f$ 出现的概率相等。所以对于任意一个样本 x,都有一半的 $f$ 下 x=1,另一半的 $f$ 下 x=0。从而有 | ||
$$ | ||
\sum_f Ⅱ(h(x) ≠ f(x)) = \frac{1}{2}2^{|X|} | ||
$$ |