如何将这篇程序的运行时间控制到1000毫秒以内？

#include <iostream>
#include <vector>
#include <numeric>
#include <limits>

using namespace std;

// 检查当前矩阵中是否有至少k个元素满足条件
int check_conditions(const vector<vector<int>>& matrix, int n, int m, int k)
{
    int count = 0;
    for (int i = 0; i < n; ++i)
    {
        int row_sum = accumulate(matrix[i].begin(), matrix[i].end(), 0);
        for (int j = 0; j < m; ++j)
        {
            int col_sum = 0;
            for (int r = 0; r < n; ++r)
            {
                col_sum += matrix[r][j];
            }
            if (matrix[i][j] >= row_sum + col_sum)
            {
                ++count;
            }
        }
    }
    return count;
}

int min_minus_operations(vector<vector<int>>& matrix, int n, int m, int k)
{
    int minus_operations = 0;

    while (true)
    {
        // 检查当前矩阵是否满足条件
        int current_count = check_conditions(matrix, n, m, k);
        if (current_count >= k)
        {
            return minus_operations;
        }

        // 对矩阵进行minus操作
        for (int i = 0; i < n; ++i)
        {
            for (int j = 0; j < m; ++j)
            {
                --matrix[i][j];
            }
        }
        ++minus_operations;
    }
}

int main()
{
    int n, m, k;
    cin >> n >> m >> k;

    vector<vector<int>> matrix(n, vector<int>(m));
    for (int i = 0; i < n; ++i)
    {
        for (int j = 0; j < m; ++j)
        {
            cin >> matrix[i][j];
        }
    }

    int result = min_minus_operations(matrix, n, m, k);
    cout << result << endl;

    return 0;
}

我把这玩意扔进 B3811 里边，后面仨测试点全 \color{00003F}{\text{TLE}} 了，求救