三分法求近是值 hdu 3714

Error Curves

Time Limit: 4000/2000 MS (Java/Others)    Memory Limit: 65536/65536 K (Java/Others)
Total Submission(s): 314    Accepted Submission(s): 109

Problem Description

Josephina is a clever girl and addicted to Machine Learning recently. She
pays much attention to a method called Linear Discriminant Analysis, which
has many interesting properties.
In order to test the algorithm's efficiency, she collects many datasets.
What's more, each data is divided into two parts: training data and test
data. She gets the parameters of the model on training data and test the
model on test data. To her surprise, she finds each dataset's test error curve is just a parabolic curve. A parabolic curve corresponds to a quadratic function. In mathematics, a quadratic function is a polynomial function of the form f(x) = ax2 + bx + c. The quadratic will degrade to linear function if a = 0.



It's very easy to calculate the minimal error if there is only one test error curve. However, there are several datasets, which means Josephina will obtain many parabolic curves. Josephina wants to get the tuned parameters that make the best performance on all datasets. So she should take all error curves into account, i.e., she has to deal with many quadric functions and make a new error definition to represent the total error. Now, she focuses on the following new function's minimum which related to multiple quadric functions. The new function F(x) is defined as follows: F(x) = max(Si(x)), i = 1...n. The domain of x is [0, 1000]. Si(x) is a quadric function. Josephina wonders the minimum of F(x). Unfortunately, it's too hard for her to solve this problem. As a super programmer, can you help her?

 

 

Input

The input contains multiple test cases. The first line is the number of cases T (T < 100). Each case begins with a number n (n ≤ 10000). Following n lines, each line contains three integers a (0 ≤ a ≤ 100), b (|b| ≤ 5000), c (|c| ≤ 5000), which mean the corresponding coefficients of a quadratic function.

 

 

Output

For each test case, output the answer in a line. Round to 4 digits after the decimal point.

 

 

Sample Input

  
  

   
   2
1
2 0 0
2
2 0 0
2 -4 2
  
  

 

 

Sample Output

  
  

   
   0.0000
0.5000
  
  

 

 

Author

LIN, Yue

 

 

Source

2010 Asia Regional Chengdu

 

 

Recommend

zhouzeyong

题目大意：函数F[x]=max{Si(x)}  （i=0，1，2，3，...，n）    其中Si(x)为二次函数， 求函数F[X]的最小值。

解题思路：用三分得到的mid1,mid2,分别到Si(x)中找最大值。

代码：

#include<iostream> #include<cmath> using namespace std; struct fun { int a,b,c; }s[10010]; double funmax(double x,int n) { int i; double Max,t; Max=s[0].a*x*x+s[0].b*x+s[0].c; for (i=1;i<n;i++) { t=s[i].a*x*x+s[i].b*x+s[i].c; if(Max<t)Max=t; } return Max; } int main() { int t,n; int i,j; double mid1,mid2,r,l,rest1,rest2; scanf("%d",&t); while(t--) { scanf("%d",&n); for(i=0;i<n;i++) { scanf("%d%d%d",&s[i].a,&s[i].b,&s[i].c); } r=0.0;l=1000.0; do { mid1=(r+l)/2; mid2=(mid1+l)/2; rest1=funmax(mid1,n); rest2=funmax(mid2,n); //printf(" %0.4lf %0.4lf %0.4lf %0.4lf /n",rest1,rest2,mid1,mid2); if(rest1>rest2)r=mid1; else l=mid2; }while(fabs(rest1-rest2)>1e-8); printf("%0.4lf/n",rest1); } return 0; }