Codeforces-The Sports Festival-贪心+dp

最新推荐文章于 2024-05-14 15:51:26 发布

云淡风轻jzl

最新推荐文章于 2024-05-14 15:51:26 发布

阅读量373

点赞数

分类专栏：贪心动态规划文章标签：贪心 dp

本文链接：https://blog.csdn.net/Nothing_but_Fight/article/details/115860648

版权

动态规划同时被 2 个专栏收录

26 篇文章

订阅专栏

贪心

7 篇文章

订阅专栏

本文介绍了一种通过调整成员顺序来最小化接力赛各阶段速度差异总和的方法。利用贪心算法确定最优区间，并结合动态规划求解最终答案。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

题目描述：

The student council is preparing for the relay race at the sports festival.

The council consists of n members. They will run one after the other in the race, the speed of member i is si. The discrepancy di of the i-th stage is the difference between the maximum and the minimum running speed among the first i members who ran. Formally, if ai denotes the speed of the i-th member who participated in the race, then di=max(a1,a2,…,ai)−min(a1,a2,…,ai)

You want to minimize the sum of the discrepancies d1+d2+⋯+dn. To do this, you are allowed to change the order in which the members run. What is the minimum possible sum that can be achieved?

输入描述：

The first line contains a single integer n (1≤n≤2000) — the number of members of the student council.
The second line contains n integers s1,s2,…,sn (1≤si≤10⁹) – the running speeds of the members.

输出描述：

Print a single integer — the minimum possible value of d1+d2+⋯+dn after choosing the order of the members.

输入样例：

6
1 6 3 3 6 3

输出样例：

大概思路：

贪心部分：dn因为包含了所有数，所以一定是全数组的最值之差。我们可以优化的是前面，让前面的值尽可能地接近，才能减少sum。因此我们将数组sort，从某一位置出发，向两端步步扩大区间[l,r]，计算sum。
dp部分：每一步扩大区间[l,r]有两种方式，l-1与r+1，此处不再符合贪心原则，而是dp。转移公式是dp[i][j]=min(dp[i+1][j],dp[i][j-1])+a[j]-a[i]。这是区间dp的退化版，先枚举长度，再枚举起点。转移来源要么i+1要么j-1，因此双重for循环内部不是o(n)的，而是o(1)的。

代码如下：

#include<cstdio>
#include<iostream>
#include<algorithm>
using namespace std;
typedef long long ll;
const int N=2020;
int a[N];
ll dp[N][N];
int main()
{
	int n;
	cin>>n;
	for(int i=0;i<n;i++)
		scanf("%d",&a[i]);
	sort(a,a+n); 
	for(int d=2;d<=n;d++)
		for(int i=0;i+d-1<n;i++)
		{
			int e=i+d-1;
			dp[i][e]=min(dp[i+1][e],dp[i][e-1])+a[e]-a[i];
		}
	cout<<dp[0][n-1]<<endl;
	return 0;
}