《统计学习方法》(第七章)—— 支持向量机

线性可分支持向量机与硬间隔最大化

线性可分支持向量机

  • 定义:给定线性可分训练数据集,通过间隔最大化或等价地求解相应的凸二次规划问题学习得到的分离超平面为
    w ∗ ⋅ x + b ∗ = 0 w^* \cdot x +b^*=0 wx+b=0
    以及相应的分类决策函数
    f ( x ) = s i g n ( w ∗ ⋅ x + b ∗ ) f(x)=sign(w^* \cdot x +b^*) f(x)=sign(wx+b)
    称为线性可分支持向量机.

函数间隔和几何间隔

  • 函数间隔定义:对于给定的训练数据集T和超平面 ( w , b ) (w,b) (w,b)定义超平面 ( w , b ) (w,b) (w,b)关于样本点 ( x i , y i ) (x_i,y_i) (xi,yi)的函数间隔为
    γ ^ i = y i ( w ⋅ x i + b ) \hat{\gamma}_i=y_i(w \cdot x_i+b) γ^i=yi(wxi+b)
    定义超平面 ( w , b ) (w,b) (w,b)关于训练数据集 T T T的函数间隔为超平面 ( w , b ) (w,b) (w,b)关于 T T T中所有样本点 ( x i , y i ) (x_i,y_i) (xi,yi)的函数间隔最小值
    γ ^ = min ⁡ i = 1 , . . . , N γ ^ i \hat{\gamma}=\min\limits_{i=1,...,N}\hat{\gamma}_i γ^=i=1,...,Nminγ^i
  • 几何间隔定义:对于给定的训练数据集 T T T和超平面 ( w , b ) (w,b) (w,b),定义超平面 ( w , b ) (w,b) (w,b)关于样本点 ( x i , y i ) (x_i,y_i) (xi,yi)的几何间隔为
    γ i = y i ( w ∣ ∣ w ∣ ∣ ⋅ x i + b ∣ ∣ w ∣ ∣ ) \gamma_i=y_i(\frac{w}{||w||}\cdot x_i+\frac{b}{||w||}) γi=yi(wwxi+wb)
    定义超平面 ( w , b ) (w,b) (w,b)关于训练数据集 T T T的几何间隔为超平面 ( w , b ) (w,b) (w,b)关于 T T T中所有样本点 ( x i , y i ) (x_i,y_i) (xi,yi)的几何间隔最小
    γ = min ⁡ i = 1 , . . . , N γ i {\gamma}=\min\limits_{i=1,...,N}{\gamma}_i γ=i=1,...,Nminγi
    于是我们有
    γ i = γ i ^ ∣ ∣ w ∣ ∣ {\gamma}_i=\frac{\hat{\gamma_i}}{||w||} γi=wγi^
    γ = γ ^ ∣ ∣ w ∣ ∣ {\gamma}=\frac{\hat{\gamma}}{||w||} γ=wγ^

间隔最大化

最大间隔超平面为
                                       max ⁡ w , b   γ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \max\limits_{w,b} \ \gamma                                       w,bmax γ
                                       s . t .      y i ( w ∣ ∣ w ∣ ∣ + b ∣ ∣ w ∣ ∣ ) ≥ γ , i = 1 , 2 , . . . , N \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ s.t. \ \ \ \ y_i(\frac{w}{||w||}+\frac{b}{||w||})\ge \gamma, i=1,2,...,N                                       s.t.    yi(ww+wb)γ,i=1,2,...,N
等价于
                                       max ⁡ w , b   γ ^ ∣ ∣ w ∣ ∣ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \max\limits_{w,b} \ \frac{\hat{\gamma}}{||w||}                                       w,bmax wγ^
                                       s . t .      y i ( w + b ) ≥ γ ^ , i = 1 , 2 , . . . , N \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ s.t. \ \ \ \ y_i({w}+{b})\ge \hat{\gamma}, i=1,2,...,N                                       s.t.    yi(w+b)γ^,i=1,2,...,N
因为 γ ^ \hat{\gamma} γ^取值无所谓,我们取 γ ^ = 1 \hat{\gamma}=1 γ^=1
则最终等价于
                                       min ⁡ w , b   1 2 ∣ ∣ w ∣ ∣ 2 \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \min\limits_{w,b} \ \frac{1}{2}||w||^2                                       w,bmin 21w2
                                       s . t .      y i ( w + b ) − 1 ≥ 0 , i = 1 , 2 , . . . , N \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ s.t. \ \ \ \ y_i({w}+{b})-1 \ge0, i=1,2,...,N                                       s.t.    yi(w+b)10,i=1,2,...,N
这是一个凸优化问题

最终算法

输入:线性可分训练数据集 T = { ( x 1 , y 1 ) , ( x 2 , y 2 ) , . . . , ( x N , y N ) } T=\{(x_1,y_1),(x_2,y_2),...,(x_N,y_N)\} T={(x1,y1),(x2,y2),...,(xN,yN)}其中 x i ∈ R n , y i ∈ { − 1 , + 1 } , i = 1 , 2 , . . . , N x_i \in R^n,y_i \in \{-1,+1\},i=1,2,...,N xiRn,yi{1,+1},i=1,2,...,N
输出:最大间隔分离超平面和分类函数

( 1 ) (1) (1)构造优化问题
                                      min ⁡ w , b   1 2 ∣ ∣ w ∣ ∣ 2 \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \min\limits_{w,b} \ \frac{1}{2}||w||^2                                      w,bmin 21w2
                                       s . t .      y i ( w + b ) − 1 ≥ 0 , i = 1 , 2 , . . . , N \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ s.t. \ \ \ \ y_i({w}+{b})-1 \ge0, i=1,2,...,N                                       s.t.    yi(w+b)10,i=1,2,...,N
( 2 ) (2) (2)得到分类超平面
w ∗ ⋅ x + b ∗ = 0 w^* \cdot x+b^*=0 wx+b=0
以及分类决策函数
f ( x ) = s i g n ( w ∗ ⋅ x + b ∗ ) f(x)=sign(w^* \cdot x+b^*) f(x)=sign(wx+b)

  • 最大间隔分离超平面存在且唯一性证明:
    ( 1 ) (1) (1)存在性
    由于数据线性可分,必然存在可行解,又由于目标函数有下界,所以最优解必然存在,记 ( w ∗ , b ∗ ) (w^*,b^*) (w,b)又因为数据中存在正负样本,所以 w ∗ ≠ 0 w^* \ne 0 w=0,存在性得证
    ( 2 ) (2) (2)唯一性
    首先证明 w ∗ w^* w唯一.假设有两个最优解 ( w 1 ∗ , b 1 ∗ ) (w_1^*,b_1^*) (w1,b1) ( w 2 ∗ , b 2 ∗ ) (w_2^*,b_2^*) (w2,b2)显然 ∣ ∣ w 1 ∗ ∣ ∣ = ∣ ∣ w 2 ∗ ∣ ∣ = c ||w_1^*||=||w_2^*||=c w1=w2=c
    w = w 1 ∗ + w 2 ∗ 2 , b = b 1 ∗ + b 2 ∗ 2 w=\frac{w_1^*+w_2^*}{2},b=\frac{b_1^*+b_2^*}{2} w=2w1+w2,b=2b1+b2,则 c ≤ ∣ ∣ w ∣ ∣ ≤ 1 2 ∣ ∣ w 1 ∗ ∣ ∣ + 1 2 ∣ ∣ w 2 ∗ ∣ ∣ = c , c\le||w||\le\frac{1}{2}||w_1^*||+\frac{1}{2}||w_2^*||=c, cw21w1+21w2=c,所以 ∣ ∣ w ∣ ∣ = 1 2 ∣ ∣ w 1 ∗ ∣ ∣ + 1 2 ∣ ∣ w 2 ∗ ∣ ∣ ||w||=\frac{1}{2}||w_1^*||+\frac{1}{2}||w_2^*|| w=21w1+21w2
    从而 ∣ ∣ w 1 ∗ ∣ ∣ = λ ∣ ∣ w 2 ∗ ∣ ∣ ||w_1^*||=\lambda||w_2^*|| w1=λw2, ∣ λ ∣ = 1 |\lambda|=1 λ=1如果 λ = − 1 \lambda=-1 λ=1,则 ∣ ∣ w ∣ ∣ = 0 ||w||=0 w=0矛盾,如果 λ = 1 \lambda=1 λ=1,则 ∣ ∣ w 1 ∗ ∣ ∣ = ∣ ∣ w 2 ∗ ∣ ∣ ||w_1^*||=||w_2^*|| w1=w2矛盾,所以 w ∗ w^* w唯一
    再证 b ∗ b^* b
    x 1 ‘ , x 2 ‘ x_1^`,x_2^` x1,x2为集合 { x i ∣ y i = + 1 } \{x_i|y_i=+1\} {xiyi=+1}中分别对应 ( w ∗ , b 1 ∗ ) (w^*,b_1^*) (w,b1) ( w ∗ , b 2 ∗ ) (w^*,b_2^*) (w,b2)成立的点
    x 1 ‘ ‘ , x 2 ‘ ‘ x_1^{``},x_2^{``} x1,x2为集合 { x i ∣ y i = − 1 } \{x_i|y_i=-1\} {xiyi=1}中分别对应 ( w ∗ , b 1 ∗ ) (w^*,b_1^*) (w,b1) ( w ∗ , b 2 ∗ ) (w^*,b_2^*) (w,b2)成立的点
    b 1 ∗ = − 1 2 ( w ∗ ⋅ x 1 ′ + w ∗ ⋅ x 1 ′ ′ ) , b 2 ∗ = − 1 2 ( w ∗ ⋅ x 2 ′ + w ∗ ⋅ x 2 ′ ′ ) b_1^*=-\frac{1}{2}(w^* \cdot x_1^{'}+w^* \cdot x_1^{''}),b_2^*=-\frac{1}{2}(w^* \cdot x_2^{'}+w^* \cdot x_2^{''}) b1=21(wx1+wx1),b2=21(wx2+wx2)
    b 1 ∗ − b 2 ∗ = − 1 2 [ w ∗ ⋅ ( x 1 ′ − x 2 ′ ) + w ∗ ⋅ ( x 1 ′ ′ − x 2 ′ ′ ) ] b_1^*-b_2^*=-\frac{1}{2}[w^*\cdot (x_1^{'}-x_2^{'})+w^*\cdot (x_1^{''}-x_2^{''})] b1b2=21[w(x1x2)+w(x1x2)]

    w ∗ ⋅ x 2 ′ + b 1 ∗ ≥ 1 = w ∗ ⋅ x 1 ′ + b 1 ∗ w^* \cdot x_2^{'}+b_1^* \ge 1=w^* \cdot x_1^{'}+b_1^* wx2+b11=wx1+b1
    w ∗ ⋅ x 1 ′ + b 1 ∗ ≥ 1 = w ∗ ⋅ x 2 ′ + b 2 ∗ w^* \cdot x_1^{'}+b_1^* \ge 1=w^* \cdot x_2^{'}+b_2^* wx1+b11=wx2+b2
    所以 w ∗ ⋅ ( x 1 ′ − x 2 ′ ) = 0 w^* \cdot(x_1^{'}-x_2^{'})=0 w(x1x2)=0,同理 w ∗ ⋅ ( x 1 ′ ‘ − x 2 ′ ’ ) = 0 w^* \cdot(x_1^{'‘}-x_2^{'’})=0 w(x1x2)=0
    所以 b 1 ∗ = b 2 ∗ b_1^*=b_2^* b1=b2成立.
  • 支持向量和间隔边界
    满足 w ⋅ x i + b = y i w \cdot x_i+b=y_i wxi+b=yi的点称为支持向量
    H 1 : w ⋅ x i + b = + 1 H_1:w \cdot x_i+b=+1 H1:wxi+b=+1
    H 2 : w ⋅ x i + b = − 1 H_2:w \cdot x_i+b=-1 H2:wxi+b=1
    H 1 和 H 2 H_1和H_2 H1H2之间的宽度为 2 ∣ ∣ w ∣ ∣ \frac{2}{||w||} w2为间隔边界

学习的对偶算法

对优化问题求解,首先定义拉格朗日函数
L ( w , b , a ) = 1 2 ∣ ∣ w ∣ ∣ 2 − ∑ i = 1 N a i y i ( w ⋅ x i + b ) + ∑ i = 1 N a i , L(w,b,a)=\frac{1}{2}||w||^2-\sum\limits_{i=1}^Na_iy_i(w \cdot x_i+b)+\sum\limits_{i=1}^Na_i, L(w,b,a)=21w2i=1Naiyi(wxi+b)+i=1Nai,其中 a i ≥ 0 , i = 1 , 2 , . . . , N a_i \ge0,i=1,2,...,N ai0,i=1,2,...,N
定义 a = ( a 1 , a 2 , . . . , a N ) T a=(a_1,a_2,...,a_N)^T a=(a1,a2,...,aN)T
则原问题等价于
max ⁡ a min ⁡ w , b L ( w , b , a ) \max\limits_a\min\limits_{w,b}L(w,b,a) amaxw,bminL(w,b,a)
( 1 ) (1) (1) min ⁡ w , b L ( w , b , a ) \min\limits_{w,b}L(w,b,a) w,bminL(w,b,a) w , b w,b w,b偏导数等于0
∇ w L ( w , b , a ) = w − ∑ i = 1 N a i y i x i = 0 \nabla_wL(w,b,a)=w-\sum\limits_{i=1}^Na_iy_ix_i=0 wL(w,b,a)=wi=1Naiyixi=0
∇ b L ( w , b , a ) = − ∑ i = 1 N a i y i = 0 \nabla_bL(w,b,a)=-\sum\limits_{i=1}^Na_iy_i=0 bL(w,b,a)=i=1Naiyi=0

w = ∑ i = 1 N a i y i x i w=\sum\limits_{i=1}^Na_iy_ix_i w=i=1Naiyixi
∑ i = 1 N a i y i = 0 \sum\limits_{i=1}^Na_iy_i=0 i=1Naiyi=0
代入得
L ( w , b , a ) = 1 2 ∑ i = 1 N ∑ j = 1 N a i a j y i y j ( x i ⋅ x j ) − ∑ i = 1 N a i y i ( ( ∑ j = 1 N a j y j x j ) ⋅ x i + b + ∑ i = 1 N a i ) L(w,b,a)=\frac{1}{2}\sum\limits_{i=1}^N\sum\limits_{j=1}^Na_ia_jy_iy_j(x_i \cdot x_j)-\sum\limits_{i=1}^Na_iy_i\Bigg((\sum\limits_{j=1}^Na_jy_jx_j)\cdot x_i +b+\sum\limits_{i=1}^Na_i\Bigg) L(w,b,a)=21i=1Nj=1Naiajyiyj(xixj)i=1Naiyi((j=1Najyjxj)xi+b+i=1Nai)

= − 1 2 ∑ i = 1 N ∑ j = 1 N a i a j y i y j ( x i ⋅ x j ) + ∑ i = 1 N a i =-\frac{1}{2}\sum\limits_{i=1}^N\sum\limits_{j=1}^Na_ia_jy_iy_j(x_i \cdot x_j)+\sum\limits_{i=1}^Na_i =21i=1Nj=1Naiajyiyj(xixj)+i=1Nai

( 2 ) (2) (2)
                                       min ⁡ a   1 2 ∑ i = 1 N ∑ j = 1 N a i a j y i y j ( x i ⋅ x j ) − ∑ i = 1 N a i \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \min\limits_a\ \frac{1}{2}\sum\limits_{i=1}^N\sum\limits_{j=1}^Na_ia_jy_iy_j(x_i \cdot x_j)-\sum\limits_{i=1}^Na_i                                       amin 21i=1Nj=1Naiajyiyj(xixj)i=1Nai
                                       s . t .    ∑ i = 1 N a i y i = 0 \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ s.t.\ \ \sum\limits_{i=1}^Na_iy_i=0                                       s.t.  i=1Naiyi=0
                                       a i ≥ 0 , i = 1 , 2 , . . . , N \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ a_i\ge 0,i=1,2,...,N                                       ai0,i=1,2,...,N



w ∗ = ∑ i = 1 N a i ∗ y i x i w^*=\sum\limits_{i=1}^Na_i^*y_ix_i w=i=1Naiyixi
b ∗ = y i − ∑ i = 1 N a i ∗ y i ( x i ⋅ x j ) , a i > 0 b^*=y_i-\sum\limits_{i=1}^Na_i^*y_i(x_i \cdot x_j),a_i>0 b=yii=1Naiyi(xixj),ai>0
f ( x ) = s i g n ( ∑ i = 1 N a i ∗ y i ( x ⋅ x i ) + b ∗ ) f(x)=sign(\sum\limits_{i=1}^Na_i^*y_i(x \cdot x_i)+b^*) f(x)=sign(i=1Naiyi(xxi)+b)
算法
输入:线性可分训练集 T = { ( x 1 , y 1 ) , ( x 2 , y 2 ) , . . . , ( x N , y N ) } T=\{(x_1,y_1),(x_2,y_2),...,(x_N,y_N)\} T={(x1,y1),(x2,y2),...,(xN,yN)},其中 x i ∈ R n , y i ∈ { − 1 , + 1 } , i = 1 , 2 , . . . , N x_i \in R^n,y_i \in \{-1,+1\},i=1,2,...,N xiRn,yi{1,+1},i=1,2,...,N
输出:分离超平面和分类决策函数
( 1 ) (1) (1)
                                       min ⁡ a   1 2 ∑ i = 1 N ∑ j = 1 N a i a j y i y j ( x i ⋅ x j ) − ∑ i = 1 N a i \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \min\limits_a\ \frac{1}{2}\sum\limits_{i=1}^N\sum\limits_{j=1}^Na_ia_jy_iy_j(x_i \cdot x_j)-\sum\limits_{i=1}^Na_i                                       amin 21i=1Nj=1Naiajyiyj(xixj)i=1Nai
                                       s . t .    ∑ i = 1 N a i y i = 0 \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ s.t.\ \ \sum\limits_{i=1}^Na_iy_i=0                                       s.t.  i=1Naiyi=0
                                       a i ≥ 0 , i = 1 , 2 , . . . , N \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ a_i\ge 0,i=1,2,...,N                                       ai0,i=1,2,...,N
求解 a ∗ a^* a
( 2 ) (2) (2)计算
w ∗ = ∑ i = 1 N a i ∗ y i x i w^*=\sum\limits_{i=1}^Na_i^*y_ix_i w=i=1Naiyixi
b ∗ = y j − ∑ i = 1 N a i ∗ y i ( x i ⋅ x j ) , a j > 0 b^*=y_j-\sum\limits_{i=1}^Na_i^*y_i(x_i \cdot x_j),a_j>0 b=yji=1Naiyi(xixj),aj>0

( 3 ) (3) (3)求得分类超平面
f ( x ) = s i g n ( ∑ i = 1 N a i ∗ y i ( x ⋅ x i ) + b ∗ ) f(x)=sign(\sum\limits_{i=1}^Na_i^*y_i(x \cdot x_i)+b^*) f(x)=sign(i=1Naiyi(xxi)+b)

线性支持向量机与软间隔最大化

线性支持向量机

  • 定义 给定线性不可分的训练数据集,通过求解凸二次规划问题,即软间隔最大化,得到分离超平面为
    w ∗ ⋅ x + b ∗ = 0 w^* \cdot x+b^*=0 wx+b=0
    以及决策分类函数
    f ( x ) = s i g n ( w ∗ ⋅ x + b ∗ ) f(x)=sign(w^* \cdot x+b^*) f(x)=sign(wx+b)
    称为线性支持向量机,

    改变约束条件为
    y i ( w ⋅ x i + b ) ≥ 1 − ξ i , ξ i ≥ 0 y_i(w \cdot x_i+b)\ge 1-\xi_i,\xi_i\ge0 yi(wxi+b)1ξi,ξi0
    目标函数为
    1 2 ∣ ∣ w ∣ ∣ 2 + C ∑ i = 1 N ξ i , C > 0 \frac{1}{2}||w||^2+C\sum\limits_{i=1}^N\xi_i,C>0 21w2+Ci=1Nξi,C>0
    最终为
    min ⁡ w , b     1 2 ∣ ∣ w ∣ ∣ 2 + C ∑ i = 1 N ξ i                           \min\limits_{w,b} \ \ \ \frac{1}{2}||w||^2+C\sum\limits_{i=1}^N\xi_i\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ w,bmin   21w2+Ci=1Nξi                         
    s . t .      y i ( w + b ) ≥ 1 − ξ i , i = 1 , 2 , . . . , N s.t. \ \ \ \ y_i({w}+{b}) \ge1-\xi_i, i=1,2,...,N s.t.    yi(w+b)1ξi,i=1,2,...,N

学习的对偶算法

根据对偶原理
L ( w , b , ξ , a , μ ) = 1 2 ∣ ∣ w ∣ ∣ 2 + C ∑ i = 1 N ξ i − ∑ i = 1 N a i ( y i ( w ⋅ x i + b ) − 1 + ξ i ) − ∑ i = 1 N μ i ξ i ,                 ξ i ≥ 0 , μ i ≥ 0 L(w,b,\xi,a,\mu)=\frac{1}{2}||w||^2+C\sum\limits_{i=1}^N\xi_i-\sum\limits_{i=1}^Na_i(y_i(w \cdot x_i+b)-1+\xi_i)-\sum_{i=1}^N\mu_i\xi_i,\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \xi_i \ge0,\mu_i\ge0 L(w,b,ξ,a,μ)=21w2+Ci=1Nξii=1Nai(yi(wxi+b)1+ξi)i=1Nμiξi,               ξi0,μi0
∇ w L ( w , b , ξ , a , μ ) = w − ∑ i = 1 N a i y i x i = 0 \nabla_wL(w,b,\xi,a,\mu)=w-\sum\limits_{i=1}^Na_iy_ix_i=0 wL(w,b,ξ,a,μ)=wi=1Naiyixi=0
∇ b L ( w , b , ξ , a , μ ) = − ∑ i = 1 N a i y i = 0 \nabla_bL(w,b,\xi,a,\mu)=-\sum\limits_{i=1}^Na_iy_i=0 bL(w,b,ξ,a,μ)=i=1Naiyi=0
∇ ξ i L ( w , b , ξ , a , μ ) = C − a i − μ i = 0 \nabla_{\xi_i}L(w,b,\xi,a,\mu)=C-a_i-\mu_i=0 ξiL(w,b,ξ,a,μ)=Caiμi=0
代入原式中得
                                  min ⁡ w , b     1 2 ∑ i = 1 N ∑ j = 1 N a i a j y i y j ( x i ⋅ x j ) − ∑ i = 1 N a i       \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \min\limits_{w,b} \ \ \ \frac{1}{2}\sum\limits_{i=1}^N\sum\limits_{j=1}^Na_ia_jy_iy_j(x_i \cdot x_j)-\sum\limits_{i=1}^Na_i \ \ \ \ \                                  w,bmin   21i=1Nj=1Naiajyiyj(xixj)i=1Nai     
s . t .              ∑ i = 1 N a i y i = 0 s.t. \ \ \ \ \ \ \ \ \ \ \ \ \sum\limits_{i=1}^Na_iy_i=0 s.t.            i=1Naiyi=0
       0 ≤ a i ≤ C , i = 1 , 2 , . . . , N \ \ \ \ \ \ 0\le a_i\le C,i=1,2,...,N       0aiC,i=1,2,...,N
其中
w ∗ = ∑ i = 1 N a i ∗ y i x i w^*=\sum\limits_{i=1}^Na_i^*y_ix_i w=i=1Naiyixi
b ∗ = y j − ∑ i = 1 N y i a i ∗ ( x i ⋅ x j ) , 0 < a j ∗ < C b^*=y_j-\sum\limits_{i=1}^Ny_ia_i^*(x_i \cdot x_j),0<a_j^*<C b=yji=1Nyiai(xixj),0<aj<C
算法:
输入:线性可分训练集 T = { ( x 1 , y 1 ) , ( x 2 , y 2 ) , . . . , ( x N , y N ) } T=\{(x_1,y_1),(x_2,y_2),...,(x_N,y_N)\} T={(x1,y1),(x2,y2),...,(xN,yN)},其中 x i ∈ R n , y i ∈ { − 1 , + 1 } , i = 1 , 2 , . . . , N x_i \in R^n,y_i \in \{-1,+1\},i=1,2,...,N xiRn,yi{1,+1},i=1,2,...,N
输出:分离超平面和分类决策函数
( 1 ) (1) (1)
                                       min ⁡ a   1 2 ∑ i = 1 N ∑ j = 1 N a i a j y i y j ( x i ⋅ x j ) − ∑ i = 1 N a i \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \min\limits_a\ \frac{1}{2}\sum\limits_{i=1}^N\sum\limits_{j=1}^Na_ia_jy_iy_j(x_i \cdot x_j)-\sum\limits_{i=1}^Na_i                                       amin 21i=1Nj=1Naiajyiyj(xixj)i=1Nai
                                       s . t .    ∑ i = 1 N a i y i = 0 \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ s.t.\ \ \sum\limits_{i=1}^Na_iy_i=0                                       s.t.  i=1Naiyi=0
                                       0 ≤ a i ≤ C , i = 1 , 2 , . . . , N \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ 0 \le a_i\le C,i=1,2,...,N                                       0aiC,i=1,2,...,N
求解 a ∗ a^* a
( 2 ) (2) (2)计算
w ∗ = ∑ i = 1 N a i ∗ y i x i w^*=\sum\limits_{i=1}^Na_i^*y_ix_i w=i=1Naiyixi
b ∗ = y j − ∑ i = 1 N a i ∗ y i ( x i ⋅ x j ) , a j > 0 b^*=y_j-\sum\limits_{i=1}^Na_i^*y_i(x_i \cdot x_j),a_j>0 b=yji=1Naiyi(xixj),aj>0

( 3 ) (3) (3)求得分类超平面
f ( x ) = s i g n ( ∑ i = 1 N a i ∗ y i ( x ⋅ x i ) + b ∗ ) f(x)=sign(\sum\limits_{i=1}^Na_i^*y_i(x \cdot x_i)+b^*) f(x)=sign(i=1Naiyi(xxi)+b)

支持向量

  • 0 < a i ∗ < C 0<a_i^*<C 0<ai<C x i x_i xi在间隔边界上
  • a i ∗ = C , 0 < ξ i < 1 a_i^*=C,0 < \xi_i <1 ai=C,0<ξi<1则分类正确,且在间隔边界和超平面之间
  • a i ∗ = C , ξ i = 1 a_i^*=C,\xi_i =1 ai=C,ξi=1 x i x_i xi在分离超平面上
  • a i ∗ = C , 1 < ξ i a_i^*=C,1 < \xi_i ai=C,1<ξi x i x_i xi在另一测

合页损失函数

修改目标函数为
∑ i = 1 N [ 1 − y i ( w ⋅ x + b ) ] + + λ ∣ ∣ w ∣ ∣ 2 \sum\limits_{i=1}^N[1-y_i(w \cdot x+b)]_++ \lambda||w||^2 i=1N[1yi(wx+b)]++λw2
等价于线性支持向量机
ξ i = [ 1 − y i ( w ⋅ x + b ) ] + \xi_i=[1-y_i(w \cdot x+b)]_+ ξi=[1yi(wx+b)]+

min ⁡ w , b ∑ i = 1 N ξ i + λ ∣ ∣ w ∣ ∣ 2 \min\limits_{w,b}\sum\limits_{i=1}^N\xi_i+\lambda||w||^2 w,bmini=1Nξi+λw2
λ = 1 2 C \lambda=\frac{1}{2C} λ=2C1

min ⁡ w , b 1 C ( C ∑ i = 1 N ξ i + 1 2 λ ∣ ∣ w ∣ ∣ 2 ) \min\limits_{w,b}\frac{1}{C}(C\sum\limits_{i=1}^N\xi_i+\frac{1}{2}\lambda||w||^2) w,bminC1(Ci=1Nξi+21λw2)
等价之

非线性支持向量机与核函数

核技巧

针对线性不可分问题,我们应用核技巧
ϕ ( x ) \phi(x) ϕ(x)为x向特征空间的映射
k ( x , z ) = ϕ ( x ) ⋅ ϕ ( z ) k(x,z)=\phi(x) \cdot \phi(z) k(x,z)=ϕ(x)ϕ(z)
替换 x j ⋅ x i x_j \cdot x_i xjxi k ( x , z ) k(x,z) k(x,z)

正定核

K ( x , z ) K(x,z) K(x,z)为正定核函数的充要条件为其Gram矩阵是半正定的
K = [ K ( x i , x j ) ] m × m K=[K(x_i,x_j)]_{m×m} K=[K(xi,xj)]m×m
为半正定

常用核函数

  • 多项式核函数
    K ( x , z ) = ( x ⋅ z + 1 ) p K(x,z)=(x \cdot z +1)^p K(x,z)=(xz+1)p
  • 高斯核函数
    K ( x , z ) = exp ⁡ ( − ∣ ∣ x − z ∣ ∣ 2 2 σ 2 ) K(x,z)=\exp(-\frac{||x-z||^2}{2\sigma^2}) K(x,z)=exp(2σ2xz2)
  • 字符串核函数
    K n ( s , t ) = ∑ u ∈ ∑ n [ ϕ n ( s ) ] n [ ϕ n ( t ) ] n = ∑ u ∈ ∑ n ∑ ( i , j ) : s ( i ) = t ( j ) = u λ l ( i ) + l ( j ) K_n(s,t)=\sum\limits_{u \in \sum^n}[\phi_n(s)]_n[\phi_n(t)]_n=\sum\limits_{u \in \sum^n}\sum\limits_{(i,j):s(i)=t(j)=u}\lambda^{l(i)+l(j)} Kn(s,t)=un[ϕn(s)]n[ϕn(t)]n=un(i,j):s(i)=t(j)=uλl(i)+l(j)
    其中 0 < λ ≤ 1 , l ( i ) 0<\lambda\le1,l(i) 0<λ1,l(i)为字符串 i i i的长度,在 s , t s,t s,t子串上进行
    l ( i ) = i ∣ u ∣ − i 1 + 1 , 1 ≤ i 1 < i 2 , . . . , i ∣ u ∣ ≤ ∣ s ∣ l(i)=i_{|u|}-i_1+1,1\le i_1<i_2,...,i_{|u|}\le |s| l(i)=iui1+1,1i1<i2,...,ius

非线性支持向量机

  • 定义:从非线性分类训练集,通过核函数与软间隔最大化,或凸规划,学习得到的分类决策函数
    f ( x ) = s i g n ( ∑ i = 1 N a i ∗ y i K ( x , x i ) + b ∗ ) f(x)=sign(\sum\limits_{i=1}^Na_i^*y_iK(x,x_i)+b^*) f(x)=sign(i=1NaiyiK(x,xi)+b)
    称为非线性支持向量机, K ( x , z ) K(x,z) K(x,z)为正定核函数
    算法:
    输入:线性可分训练集 T = { ( x 1 , y 1 ) , ( x 2 , y 2 ) , . . . , ( x N , y N ) } T=\{(x_1,y_1),(x_2,y_2),...,(x_N,y_N)\} T={(x1,y1),(x2,y2),...,(xN,yN)},其中 x i ∈ R n , y i ∈ { − 1 , + 1 } , i = 1 , 2 , . . . , N x_i \in R^n,y_i \in \{-1,+1\},i=1,2,...,N xiRn,yi{1,+1},i=1,2,...,N
    输出:分离超平面和分类决策函数
    ( 1 ) (1) (1)
                                           min ⁡ a   1 2 ∑ i = 1 N ∑ j = 1 N a i a j y i y j K ( x i , x j ) − ∑ i = 1 N a i \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \min\limits_a\ \frac{1}{2}\sum\limits_{i=1}^N\sum\limits_{j=1}^Na_ia_jy_iy_jK(x_i,x_j)-\sum\limits_{i=1}^Na_i                                       amin 21i=1Nj=1NaiajyiyjK(xi,xj)i=1Nai
                                           s . t .    ∑ i = 1 N a i y i = 0 \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ s.t.\ \ \sum\limits_{i=1}^Na_iy_i=0                                       s.t.  i=1Naiyi=0
                                           0 ≤ a i ≤ C , i = 1 , 2 , . . . , N \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ 0 \le a_i\le C,i=1,2,...,N                                       0aiC,i=1,2,...,N
    求解 a ∗ a^* a
    ( 2 ) (2) (2)计算
    w ∗ = ∑ i = 1 N a i ∗ y i x i w^*=\sum\limits_{i=1}^Na_i^*y_ix_i w=i=1Naiyixi
    b ∗ = y j − ∑ i = 1 N a i ∗ y i K ( x i , x j ) , a j > 0 b^*=y_j-\sum\limits_{i=1}^Na_i^*y_iK(x_i,x_j),a_j>0 b=yji=1NaiyiK(xi,xj),aj>0

( 3 ) (3) (3)求得分类超平面
f ( x ) = s i g n ( ∑ i = 1 N a i ∗ y i K ( x i , x ) + b ∗ ) f(x)=sign(\sum\limits_{i=1}^Na_i^*y_iK(x_i,x)+b^*) f(x)=sign(i=1NaiyiK(xi,x)+b)

序列最小最优化算法

选择两个违反KKT条件的变量进行优化,直到满足停止条件或者都满足KKT条件,如果满足KKT条件,则是最优解

两个变量二次规划的求解方法

设选择 a 1 , a 2 a_1,a_2 a1,a2
min ⁡ a 1 , a 2       W ( a 1 , a 2 ) = 1 2 K 11 a 1 2 + 1 2 K 22 a 2 2 + y 1 y 2 K 12 a 1 a 2 − ( a 1 + a 2 ) + y 1 a 1 ∑ i = 3 N y i a i K i 1 + y 2 a 2 ∑ i = 3 N y i a i K i 2 \min\limits_{a_1,a_2}\ \ \ \ \ W(a_1,a_2)=\frac{1}{2}K_{11}a_1^2+\frac{1}{2}K_{22}a_2^2+y_1y_2K_{12}a_1a_2-(a_1+a_2)+y_1a_1\sum\limits_{i=3}^Ny_ia_iK_{i1}+y_2a_2\sum\limits_{i=3}^Ny_ia_iK_{i2} a1,a2min     W(a1,a2)=21K11a12+21K22a22+y1y2K12a1a2(a1+a2)+y1a1i=3NyiaiKi1+y2a2i=3NyiaiKi2
s . t .          a 1 y 1 + a 2 y 2 = − ∑ i = 3 N y i a i = ξ s.t.\ \ \ \ \ \ \ \ a_1y_1+a_2y_2=-\sum\limits_{i=3}^Ny_ia_i=\xi s.t.        a1y1+a2y2=i=3Nyiai=ξ
              0 ≤ a i ≤ C , i = 1 , 2 \ \ \ \ \ \ \ \ \ \ \ \ \ 0 \le a_i \le C,i=1,2              0aiC,i=1,2
K i j = K ( x i , x j ) K_{ij}=K(x_i,x_j) Kij=K(xi,xj)
我们要求
L ≤ a 2 n e w ≤ H L \le a_2^{new}\le H La2newH

  • y 1 ≠ y 2 y_1\ne y_2 y1=y2 L = max ⁡ ( 0 , a 2 o l d − a 1 o l d ) , R = min ⁡ ( C , C + a 2 o l d − a 1 o l d ) L=\max(0,a_2^{old}-a_1^{old}),R=\min(C,C+a_2^{old}-a_1^{old}) L=max(0,a2olda1old),R=min(C,C+a2olda1old)

  • y 1 = y 2 y_1= y_2 y1=y2 L = max ⁡ ( 0 , a 2 o l d + a 1 o l d − C ) , R = min ⁡ ( C , a 2 o l d + a 1 o l d ) L=\max(0,a_2^{old}+a_1^{old}-C),R=\min(C,a_2^{old}+a_1^{old}) L=max(0,a2old+a1oldC),R=min(C,a2old+a1old)
    未剪辑和考虑约束条件的解为 a 2 n e w , u n c a_2^{new,unc} a2new,unc
    g ( x ) = ∑ i = 1 N a i y i K ( x i , x ) + b g(x)=\sum\limits_{i=1}^Na_iy_iK(x_i,x)+b g(x)=i=1NaiyiK(xi,x)+b
    E i = g ( x i ) − y i = ( ∑ j = 1 N a j y j K ( x j , x i ) + b ) − y i ,       i = 1 , 2 E_i=g(x_i)-y_i=(\sum\limits_{j=1}^Na_jy_jK(x_j,x_i)+b)-y_i,\ \ \ \ \ i=1,2 Ei=g(xi)yi=(j=1NajyjK(xj,xi)+b)yi,     i=1,2

    a 2 n e w , u n c = a 2 o l d + y 2 ( E 1 − E 2 ) η a_2^{new,unc}=a_2^{old}+\frac{y_2(E_1-E_2)}{\eta} a2new,unc=a2old+ηy2(E1E2)
    其中
    η = K 11 + K 22 − 2 K 12 \eta=K_{11}+K_{22}-2K_{12} η=K11+K222K12
    再进行剪辑
    a n e w = { H a 2 n e w , u n c > H a 2 n e w , u n c L ≤ a 2 n e w , u n c ≤ H L a 2 n e w , u n c < L a^{new}=\begin{cases} H & a_2^{new,unc}>H\\ a_2^{new,unc} & L \le a_2^{new,unc} \le H\\ L & a_2^{new,unc}<L\\ \end{cases} anew=Ha2new,uncLa2new,unc>HLa2new,uncHa2new,unc<L

    a 1 n e w = a 1 o l d + y 1 y 2 ( a 2 o l d − a 1 o l d ) a_1^{new}=a_1^{old}+y_1y_2(a_2^{old}-a_1^{old}) a1new=a1old+y1y2(a2olda1old)

  • 以上更新公式的证明:
    v i = ∑ j = 3 N a j y j K ( x i , x j ) = g ( x i ) − ∑ j = 1 2 a j y j K ( x i , x j ) − b v_i=\sum\limits_{j=3}^Na_jy_jK(x_i,x_j)=g(x_i)-\sum\limits_{j=1}^2a_jy_jK(x_i,x_j)-b vi=j=3NajyjK(xi,xj)=g(xi)j=12ajyjK(xi,xj)b
    则原问题为
    W ( a 1 , a 2 ) = 1 2 K 11 a 1 2 + 1 2 K 22 a 2 2 + y 1 y 2 K 12 a 1 a 2 − ( a 1 + a 2 ) + y 1 v 1 a 1 + y 2 v 2 a 2 W(a_1,a_2)=\frac{1}{2}K_{11}a_1^2+\frac{1}{2}K_{22}a_2^2+y_1y_2K_{12}a_1a_2-(a_1+a_2)+y_1v_1a_1+y_2v_2a_2 W(a1,a2)=21K11a12+21K22a22+y1y2K12a1a2(a1+a2)+y1v1a1+y2v2a2

    a 1 = ( ξ − y 2 a 2 ) y 1 a_1=(\xi-y_2a_2)y_1 a1=(ξy2a2)y1
    则得到
    W ( a 2 ) = 1 2 K 11 ( ξ − a 2 y 2 ) 2 + 1 2 K 22 a 2 2 + y 2 K 12 ( ξ − a 2 y 2 ) a 2 − ( ξ − a 2 y 2 ) y 1 − a 2 + v 1 ( ξ − a 2 y 2 ) + y 2 v 2 a 2 W(a_2)=\frac{1}{2}K_{11}(\xi-a_2y_2)^2+\frac{1}{2}K_{22}a_2^2+y_2K_{12}(\xi-a_2y_2)a_2-(\xi-a_2y_2)y_1-a_2+v_1(\xi-a_2y_2)+y_2v_2a_2 W(a2)=21K11(ξa2y2)2+21K22a22+y2K12(ξa2y2)a2(ξa2y2)y1a2+v1(ξa2y2)+y2v2a2
    求导
    ∂ W ∂ a 2 = K 11 a 2 + K 22 a 2 − 2 K 12 a 2 − K 11 ξ y 2 + K 12 ξ y 2 + y 1 y 2 − 1 − v 1 y 2 + y 2 v 2 = 0 \frac{\partial W}{\partial a_2}=K_{11}a_2+K_{22}a_2-2K_{12}a_2-K_{11}\xi y_2+K_{12}\xi y_2+y_1y_2-1-v_1y_2+y_2v_2=0 a2W=K11a2+K22a22K12a2K11ξy2+K12ξy2+y1y21v1y2+y2v2=0
    同时
    η = K 11 + K 22 − 2 K 12 \eta=K_{11}+K_{22}-2K_{12} η=K11+K222K12

    a 2 n e w , u n c = a 2 o l d + y 2 ( E 1 − E 2 ) η a_2^{new,unc}=a_2^{old}+\frac{y_2(E_1-E_2)}{\eta} a2new,unc=a2old+ηy2(E1E2)

变量的选择方法

  1. 选择第一个变量
    KTT条件如下
    a i = 0    ⟺    y i g ( x i ) ≥ 1 a_i=0\iff y_ig(x_i) \ge 1 ai=0yig(xi)1
    0 < a i < C    ⟺    y i g ( x i ) = 1 0<a_i<C\iff y_ig(x_i) = 1 0<ai<Cyig(xi)=1
    a i = C    ⟺    y i g ( x i ) ≤ 1 a_i=C\iff y_ig(x_i) \le 1 ai=Cyig(xi)1
    优先选择不满足第二个条件,再遍历整个数据集选其他不满足的
  2. 选择第二个变量
    在第一个选择后,我们选择 a 2 a_2 a2的原则是尽量变化的快,即
  • E 1 > 0 E_1>0 E1>0,选最小的 E 2 E_2 E2
  • E 1 < 0 E_1<0 E1<0,选最大的 E 2 E_2 E2
    优先选择间隔边界上的点,如果没有变化快的,则遍历整个数据集,如果再没有,则放弃 a 1 a_1 a1重新选择 a 1 a_1 a1
  1. 计算 b b b E i E_i Ei
    由KKT条件, 0 < a 1 n e w < C 0<a_1^{new}<C 0<a1new<C
    ∑ i = 1 N a i y i K i 1 + b = y 1 \sum\limits_{i=1}^Na_iy_iK_{i1}+b=y_1 i=1NaiyiKi1+b=y1

    b 1 n e w = y 1 − ∑ i = 3 N a i y i K i 1 − a 1 n e w y 1 K 11 − a 2 n e w y 2 K 21 b_1^{new}=y_1-\sum\limits_{i=3}^Na_iy_iK_{i1}-a_1^{new}y_1K_{11}-a_2^{new}y_2K_{21} b1new=y1i=3NaiyiKi1a1newy1K11a2newy2K21

    E 1 = ∑ i = 3 N a i y i K i 1 + a 1 o l d y 1 K 11 + a 2 o l d y 2 K 21 + b o l d − y 1 E_1=\sum\limits_{i=3}^Na_iy_iK_{i1}+a_1^{old}y_1K_{11}+a_2^{old}y_2K_{21}+b^{old}-y_1 E1=i=3NaiyiKi1+a1oldy1K11+a2oldy2K21+boldy1
    由两项得
    b 1 n e w = − E 1 − y 1 K 11 ( a 1 n e w − a 1 o l d ) − y 2 K 21 ( a 2 n e w − a 2 o l d ) + b o l d b_1^{new}=-E_1-y_1K_{11}(a_1^{new}-a_1^{old})-y_2K_{21}(a_2^{new}-a_2^{old})+b^{old} b1new=E1y1K11(a1newa1old)y2K21(a2newa2old)+bold
    同样如果 0 < a 2 n e w < C 0<a_2^{new}<C 0<a2new<C
    b 2 n e w = − E 2 − y 1 K 12 ( a 1 n e w − a 1 o l d ) − y 2 K 22 ( a 2 n e w − a 2 o l d ) + b o l d b_2^{new}=-E_2-y_1K_{12}(a_1^{new}-a_1^{old})-y_2K_{22}(a_2^{new}-a_2^{old})+b^{old} b2new=E2y1K12(a1newa1old)y2K22(a2newa2old)+bold
    如果 a 1 n e w , a 2 n e w a_1^{new},a_2^{new} a1new,a2new同时满足条件,则 b 1 n e w = b 2 n e w b_1^{new}=b_2^{new} b1new=b2new
    如果 a 1 n e w , a 2 n e w a_1^{new},a_2^{new} a1new,a2new为0或 C C C,则我们取 b n e w = b 1 n e w + b 2 n e w 2 b^{new}=\frac{b_1^{new}+b_2^{new}}{2} bnew=2b1new+b2new
    最后
    E i n e w = ∑ S y j a j K ( x i , x j ) + b n e w − y i E_i^{new}=\sum\limits_{S}y_ja_jK(x_i,x_j)+b^{new}-y_i Einew=SyjajK(xi,xj)+bnewyi
    其中 S S S为支持向量的集合

SMO算法

输入:训练数据集 T = { ( x 1 , y 1 ) , ( x 2 , y 2 ) , . . . , ( x N , y N ) } , x i ∈ R n , y i ∈ { − 1 , + 1 } T=\{(x_1,y_1),(x_2,y_2),...,(x_N,y_N)\},x_i \in R^n,y_i \in \{-1,+1\} T={(x1,y1),(x2,y2),...,(xN,yN)},xiRn,yi{1,+1},精度 ϵ \epsilon ϵ
输出:近似解 a ^ \hat{a} a^
( 1 ) (1) (1)取初始值 a ( 0 ) = 0 , k = 0 a^{(0)}=0,k=0 a(0)=0,k=0
( 2 ) (2) (2)按照算法求解以 a 1 ( k ) a 2 ( k ) , a^{(k)}_1a^{(k)}_2, a1(k)a2(k), a 1 ( k + 1 ) a 2 ( k + 1 ) , a^{(k+1)}_1a^{(k+1)}_2, a1(k+1)a2(k+1),
( 3 ) (3) (3)如果以精度 ϵ \epsilon ϵ满足条件则停止,
∑ i = 1 N a i y i = 0 , 0 ≤ a i ≤ C , i = 1 , 2 , . . . , N \sum\limits_{i=1}^Na_iy_i=0,0\le a_i \le C,i=1,2,...,N i=1Naiyi=0,0aiC,i=1,2,...,N
y i ⋅ g ( x i ) = { ≥ 1 { x i ∣ a i = 0 } = 1 { x i ∣ 0 < a i < C } ≤ 1 { x i ∣ a i = C } y_i \cdot g(x_i)=\begin{cases} \ge 1 &\{x_i|a_i=0\}\\ =1 &\{x_i|0<a_i<C\}\\ \le 1 & \{x_i|a_i=C\}\\ \end{cases} yig(xi)=1=11{xiai=0}{xi0<ai<C}{xiai=C}
其中
g ( x i ) = ∑ j = 1 N a j y j K ( x j , x i ) + b g(x_i)=\sum\limits_{j=1}^Na_jy_jK(x_j,x_i)+b g(xi)=j=1NajyjK(xj,xi)+b
否则转 ( 4 ) , k = k + 1 (4),k=k+1 (4),k=k+1
( 4 ) (4) (4) a ^ = a ( k + 1 ) \hat{a}=a^{(k+1)} a^=a(k+1)

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值