linear regression

最新推荐文章于 2024-09-12 17:00:39 发布

hejiwen2001

最新推荐文章于 2024-09-12 17:00:39 发布

阅读量389

点赞数

本文链接：https://blog.csdn.net/hejiwen2001/article/details/8756982

版权

本文通过C语言实现线性回归，介绍了批量梯度下降和随机梯度下降两种优化算法，并对比了它们的收敛速度及效果。同时，文中还提供了MATLAB中解析法求解线性回归的示例。

摘要由CSDN通过智能技术生成

#include <stdio.h>
#define M 10

//todo：多个Feather的情况
//todo: 考虑非线性回归问题

//is convergence
//todo:使用两次更新theta时，J变化很小作为收敛条件
int is_convergence(int sample[M][2],double *theta)
{
   double J = 0;
   double h = 0;
   int i;

   for(i = 0; i < M; i++)
   {
       h = theta[0] + theta[1]*sample[i][0];
       J += (h - sample[i][1])*(h - sample[i][1]);
   }

   J *= 0.5;
   if(J < 1e-15)
       return 1;
   else
       return 0;
}

//批量梯度下降
void batch_gradient_descent(int sample[M][2], double alpha, double *theta)
{
   int i;
   int count = 0;
   double J = 0;
   double h = 0;

   while(1)
   {
       //update theta
       double error_sum1 = 0;
       double error_sum2 = 0;
       for(i = 0; i < M; i++)
       {
           h = theta[0]+theta[1]*sample[i][0];
           error_sum1 += (sample[i][1]-h)*1;
           error_sum2 += (sample[i][1]-h)*sample[i][0];
       }
       theta[0] += alpha * error_sum1;
       theta[1] += alpha * error_sum2;

       if(is_convergence(sample,theta))
           break;

       count++;
   }

   fprintf(stderr, "batch_theta = %f batch_theta = %f\n", theta[0],theta[1]);
   fprintf(stderr, "batch_count = %d\n",count);
}

//随机梯度下降
void stochastic_gradient(int sample[M][2], double alpha,double *theta)
{
   double J = 0;
   double h = 0;

   int random = 0;
   int count = 0;
   //int i;
   //for(i = 0; i < 100; i++)
   while(1)
   {
       //update theta
       int j = (random+=3) % M;//todo:改为随机选择

       h = theta[0]+theta[1]*sample[j][0];
       theta[0] += alpha * (sample[j][1]-h);
       theta[1] += alpha * (sample[j][1]-h)*sample[j][0];

       if(is_convergence(sample,theta))
           break;

       count++;
   }
   fprintf(stderr, "stoch_theta = %f stock_theta = %f\n", theta[0],theta[1]);
   fprintf(stderr, "stoch_count = %d\n",count);
}

int main()
{
   //prepare data
   int sample[M][2];
   int i;
   for(i = 0; i < M; i++)
   {
       sample[i][0] = i;
       sample[i][1] = 4+11*i; //4+11x
   }

    //alpha is very important
   double batch_alpha = 0.000006071;
   double batch_theta[2]={1000,4000};
   batch_gradient_descent(sample,batch_alpha,batch_theta);

    double stoch_alpha = 0.00061;
   double stoch_theta[2]={1000,-40000000};
   stochastic_gradient(sample,stoch_alpha,stoch_theta);
   return 0;

}

MATLAB:

x=[1:1:100]';
y=3*x+4;
x = reshape([ones(100,1);x],100,2);
theta=inv(x'*x)*x'*y

y=x * theta