我是靠谱客的博主 完美小蘑菇,最近开发中收集的这篇文章主要介绍【机器学习】逻辑回归——数学原理推导,觉得挺不错的,现在分享给大家,希望可以做个参考。

概述

以逻辑回归的二分类模型作出如下推导:

1. 定义
在线性回归上套一层sigmoid函数
g ( z ) = 1 1 + e − z g(z) = frac{1}{1 + e^{-z}} g(z)=1+ez1

y = h θ ( x ) = g ( θ T x ) = 1 1 + e − θ T x = 1 1 + e − ( θ 0 + θ 1 x 1 + θ 2 x 2 + . . . + θ n x n ) y = h_theta(x) = g(theta^Tx) = frac{1}{1 + e^{-theta^Tx}} = frac{1}{1 + e^{-(theta_0 + theta_1x_1 + theta_2x_2 + ... + theta_nx_n)}} y=hθ(x)=g(θTx)=1+eθTx1=1+e(θ0+θ1x1+θ2x2+...+θnxn)1

注: x 0 x_0 x0是为了便于计算,人为增添的一列,值全为1

这里对函数 g ( z ) g(z) g(z)进行下求导运算,后面推导会用到。

g ′ ( z ) = ( 1 1 + e − z ) ′ g'(z) = (frac{1}{1 + e^{-z}})' g(z)=(1+ez1)

= e − z + 1 − 1 ( 1 + e − z ) 2 quadquad=frac{e^{-z} +1-1}{{(1+e^{-z})}^2} =(1+ez)2ez+11

= 1 1 + e − z − 1 ( 1 + e − z ) 2 quadquad=frac{1}{1+e^{-z}} - frac{1}{{(1+e^{-z})}^2} =1+ez1(1+ez)21

= g ( z ) ( 1 − g ( z ) ) quadquad=g(z)(1-g(z)) =g(z)(1g(z))

2. 计算概率
假定:

  • p ( y = 1 ∣ x ; θ ) = h θ ( x ) p(y=1|x;theta) = h_theta(x) p(y=1x;θ)=hθ(x)
  • p ( y = 0 ∣ x ; θ ) = 1 − h θ ( x ) p(y=0|x;theta) = 1 - h_theta(x) p(y=0x;θ)=1hθ(x)

组合上述两式:

p ( y ∣ x θ ) = h θ ( x ) y i ( 1 − h θ ( x ) ) 1 − y i p(y|xtheta) = h_theta(x)^{y_i}(1-h_theta(x))^{1-y_i} p(yxθ)=hθ(x)yi(1hθ(x))1yi

y y y是标签,正类标记1,负类标记0

3. 极大似然估计

L ( θ ) = ∏ i = 1 m ( h θ ( x i ) y i ( 1 − h θ ( x i ) ) 1 − y i ) ) L(theta) = prod_{i=1}^{m}{(h_theta(x_i)^{y_i}(1-h_theta(x_i))^{1-y_i}))} L(θ)=i=1m(hθ(xi)yi(1hθ(xi))1yi))

取对数,转累加

l ( θ ) = ln ⁡ L ( θ ) l(theta) = ln L(theta) l(θ)=lnL(θ)

= ∑ i = 1 m ln ⁡ ( h θ ( x i ) y i ( 1 − h θ ( x i ) ) 1 − y i ) ) quad =sum_{i=1}^{m}{ln(h_theta(x_i)^{y_i}(1-h_theta(x_i))^{1-y_i}))} =i=1mln(hθ(xi)yi(1hθ(xi))1yi))

= ∑ i = 1 m [ y i ln ⁡ h θ ( x i ) + ( 1 − y i ) ln ⁡ ( 1 − h θ ( x i ) ) ] quad =sum_{i=1}^{m}{[y_i ln h_theta(x_i) + (1-y_i)ln(1-h_theta(x_i))]} =i=1m[yilnhθ(xi)+(1yi)ln(1hθ(xi))]

说明:

  • 当y=1时,我们期望 p ( y = 1 ∣ x ; θ ) p(y=1|x;theta) p(y=1x;θ)的值越大,即预测结果为正类的概率越大,误差就越小
  • 当y=0时,我们期望 p ( y = 0 ∣ x ; θ ) p(y=0|x;theta) p(y=0x;θ)的值越大,即预测结果为负类的概率越大,误差也越小

因此我们的目标是求取似然函数 l ( θ ) l(theta) l(θ)的最大值。

4. 损失函数

对似然函数求最大值需要使用梯度上升的方式,这里我们引入 J ( θ ) = − l ( θ ) J(theta) = -l(theta) J(θ)=l(θ),转化为使用梯度下降的方式计算损失函数的最小值。

5. 梯度下降

∂ ∂ θ J ( θ j ) = − ∂ ∂ θ ∑ i = 1 m [ y i ln ⁡ h θ ( x i ) + ( 1 − y i ) ln ⁡ ( 1 − h θ ( x i ) ) ] frac{partial}{partialtheta}J(theta_j) = -frac{partial}{partialtheta}sum_{i=1}^{m}{[y_i ln h_theta(x_i) + (1-y_i)ln(1-h_theta(x_i))]} θJ(θj)=θi=1m[yilnhθ(xi)+(1yi)ln(1hθ(xi))]

= − ∑ i = 1 m [ y i 1 h θ ( x i ) ∂ ∂ θ h θ ( x i ) − ( 1 − y i ) 1 1 − h θ ( x i ) ∂ ∂ θ h θ ( x i ) ] quadquadquad = -sum_{i=1}^{m}{[y_ifrac{1}{h_theta(x_i)}frac{partial}{partial theta} h_theta(x_i)-(1-y_i)frac{1}{1-h_theta(x_i)}frac{partial}{partial theta} h_theta(x_i)]} =i=1m[yihθ(xi)1θhθ(xi)(1yi)1hθ(xi)1θhθ(xi)]

= − ∑ i = 1 m [ y i 1 h θ ( x i ) − ( 1 − y i ) 1 1 − h θ ( x i ) ] ∂ ∂ θ h θ ( x i ) quadquadquad = -sum_{i=1}^{m}{[y_ifrac{1}{h_theta(x_i)} - (1-y_i)frac{1}{1-h_theta(x_i)}]}frac{partial}{partial theta} h_theta(x_i) =i=1m[yihθ(xi)1(1yi)1hθ(xi)1]θhθ(xi)

= − ∑ i = 1 m [ y i 1 g ( θ T x ) − ( 1 − y i ) 1 1 − g ( θ T x ) ] ∂ ∂ θ g ( θ T x ) quadquadquad = -sum_{i=1}^{m}{[y_ifrac{1}{g(theta^Tx)} - (1-y_i)frac{1}{1-g(theta^Tx)}]}frac{partial}{partial theta} g(theta^Tx) =i=1m[yig(θTx)1(1yi)1g(θTx)1]θg(θTx)

= − ∑ i = 1 m [ y i 1 g ( θ T x ) − ( 1 − y i ) 1 1 − g ( θ T x ) ] g ( θ T x ) ( 1 − g ( θ T x ) ) ∂ ∂ θ θ T x quadquadquad = -sum_{i=1}^{m}{[y_ifrac{1}{g(theta^Tx)} - (1-y_i)frac{1}{1-g(theta^Tx)}]}g(theta^Tx)(1-g(theta^Tx))frac{partial}{partial theta}theta^Tx =i=1m[yig(θTx)1(1yi)1g(θTx)1]g(θTx)(1g(θTx))θθTx

= − ∑ i = 1 m [ y i ( 1 − g ( θ T x ) ) − ( 1 − y i ) g ( θ T x ) ] x i ( j ) quadquadquad = -sum_{i=1}^{m}{[y_i(1-g(theta^Tx)) - (1-y_i)g(theta^Tx)]}x_i^{(j)} =i=1m[yi(1g(θTx))(1yi)g(θTx)]xi(j)

= − ∑ i = 1 m [ y i − g ( θ T x ) ] x i ( j ) quadquadquad = -sum_{i=1}^{m}{[y_i - g(theta^Tx)]}x_i^{(j)} =i=1m[yig(θTx)]xi(j)

= ∑ i = 1 m ( h θ ( x i ) − y i ) x i ( j ) quadquadquad = sum_{i=1}^{m}{(h_theta(x_i) - y_i)}x_i^{(j)} =i=1m(hθ(xi)yi)xi(j)

更新参数:

θ j : = θ j − α ∑ i = 1 m ( h θ ( x i ) − y i ) x i ( j ) theta_j := theta_j - alphasum_{i=1}^{m}{(h_theta(x_i) - y_i)}x_i^{(j)} θj:=θjαi=1m(hθ(xi)yi)xi(j)

最后

以上就是完美小蘑菇为你收集整理的【机器学习】逻辑回归——数学原理推导的全部内容,希望文章能够帮你解决【机器学习】逻辑回归——数学原理推导所遇到的程序开发问题。

如果觉得靠谱客网站的内容还不错,欢迎将靠谱客网站推荐给程序员好友。

本图文内容来源于网友提供,作为学习参考使用,或来自网络收集整理,版权属于原作者所有。
点赞(53)

评论列表共有 0 条评论

立即
投稿
返回
顶部