虽然不是很确定O(n)复杂度，但肯定在O(n)和nLog(n)之间。也肯定更接近于O(n)而不是nLog(n)函数是用Java编写的

public int quickSelect(ArrayList<Integer>list, int nthSmallest){
    //Choose random number in range of 0 to array length
    Random random =  new Random();
    //This will give random number which is not greater than length - 1
    int pivotIndex = random.nextInt(list.size() - 1); 

    int pivot = list.get(pivotIndex);

    ArrayList<Integer> smallerNumberList = new ArrayList<Integer>();
    ArrayList<Integer> greaterNumberList = new ArrayList<Integer>();

    //Split list into two. 
    //Value smaller than pivot should go to smallerNumberList
    //Value greater than pivot should go to greaterNumberList
    //Do nothing for value which is equal to pivot
    for(int i=0; i<list.size(); i++){
        if(list.get(i)<pivot){
            smallerNumberList.add(list.get(i));
        }
        else if(list.get(i)>pivot){
            greaterNumberList.add(list.get(i));
        }
        else{
            //Do nothing
        }
    }

    //If smallerNumberList size is greater than nthSmallest value, nthSmallest number must be in this list 
    if(nthSmallest < smallerNumberList.size()){
        return quickSelect(smallerNumberList, nthSmallest);
    }
    //If nthSmallest is greater than [ list.size() - greaterNumberList.size() ], nthSmallest number must be in this list
    //The step is bit tricky. If confusing, please see the above loop once again for clarification.
    else if(nthSmallest > (list.size() - greaterNumberList.size())){
        //nthSmallest will have to be changed here. [ list.size() - greaterNumberList.size() ] elements are already in 
        //smallerNumberList
        nthSmallest = nthSmallest - (list.size() - greaterNumberList.size());
        return quickSelect(greaterNumberList,nthSmallest);
    }
    else{
        return pivot;
    }
}

下面是完整实现的链接，其中相当广泛地解释了在无序算法中查找第k个元素的算法是如何工作的。基本思想是像快速排序一样对数组进行分区。但为了避免极端情况(例如每一步都选择最小的元素作为主元，使算法运行时间退化为O(n^2))，采用特殊的主元选择，称为中位数的中位数算法。在最坏情况和平均情况下，整个解在O(n)时间内运行。

这里是全文的链接(它是关于寻找第k个最小的元素，但寻找第k个最大的元素的原理是相同的):

在无序数组中寻找第k个最小元素

下面是eladv建议的算法的实现(我也把随机pivot的实现放在这里):

public class Median {

    public static void main(String[] s) {

        int[] test = {4,18,20,3,7,13,5,8,2,1,15,17,25,30,16};
        System.out.println(selectK(test,8));

        /*
        int n = 100000000;
        int[] test = new int[n];
        for(int i=0; i<test.length; i++)
            test[i] = (int)(Math.random()*test.length);

        long start = System.currentTimeMillis();
        random_selectK(test, test.length/2);
        long end = System.currentTimeMillis();
        System.out.println(end - start);
        */
    }

    public static int random_selectK(int[] a, int k) {
        if(a.length <= 1)
            return a[0];

        int r = (int)(Math.random() * a.length);
        int p = a[r];

        int small = 0, equal = 0, big = 0;
        for(int i=0; i<a.length; i++) {
            if(a[i] < p) small++;
            else if(a[i] == p) equal++;
            else if(a[i] > p) big++;
        }

        if(k <= small) {
            int[] temp = new int[small];
            for(int i=0, j=0; i<a.length; i++)
                if(a[i] < p)
                    temp[j++] = a[i];
            return random_selectK(temp, k);
        }

        else if (k <= small+equal)
            return p;

        else {
            int[] temp = new int[big];
            for(int i=0, j=0; i<a.length; i++)
                if(a[i] > p)
                    temp[j++] = a[i];
            return random_selectK(temp,k-small-equal);
        }
    }

    public static int selectK(int[] a, int k) {
        if(a.length <= 5) {
            Arrays.sort(a);
            return a[k-1];
        }

        int p = median_of_medians(a);

        int small = 0, equal = 0, big = 0;
        for(int i=0; i<a.length; i++) {
            if(a[i] < p) small++;
            else if(a[i] == p) equal++;
            else if(a[i] > p) big++;
        }

        if(k <= small) {
            int[] temp = new int[small];
            for(int i=0, j=0; i<a.length; i++)
                if(a[i] < p)
                    temp[j++] = a[i];
            return selectK(temp, k);
        }

        else if (k <= small+equal)
            return p;

        else {
            int[] temp = new int[big];
            for(int i=0, j=0; i<a.length; i++)
                if(a[i] > p)
                    temp[j++] = a[i];
            return selectK(temp,k-small-equal);
        }
    }

    private static int median_of_medians(int[] a) {
        int[] b = new int[a.length/5];
        int[] temp = new int[5];
        for(int i=0; i<b.length; i++) {
            for(int j=0; j<5; j++)
                temp[j] = a[5*i + j];
            Arrays.sort(temp);
            b[i] = temp[2];
        }

        return selectK(b, b.length/2 + 1);
    }
}

c++标准库几乎完全有这个函数调用nth_element，尽管它确实会修改数据。它有线性运行时间，O(N)，它也做部分排序。

const int N = ...;
double a[N];
// ... 
const int m = ...; // m < N
nth_element (a, a + m, a + N);
// a[m] contains the mth element in a

根据本文，在n个项目的列表中寻找第k个最大的项目，下面的算法在最坏的情况下将花费O(n)时间。

将数组分成n/5个列表，每个列表有5个元素。 求每个5个元素的子数组的中值。 递归地找到所有中位数的中位数，记作M 将数组划分为两个子数组第一个子数组包含大于M的元素，设这个子数组为a1，而其他子数组包含小于M的元素，设这个子数组为a2。 如果k <= |a1|，返回选择(a1,k)。 k−1 = |a1|，返回M。 如果k> |a1| + 1，返回选择(a2,k−a1−1)。

分析:如原文所述:

我们使用中位数将列表分成两部分(前一半， 如果k <= n/2，反之则为后半部分)。这个算法需要 对于某个常数c，递归第一级的时间cn/2 at 下一层(因为我们在大小为n/2的列表中递归)，cn/4在 第三层，以此类推。总时间为cn + cn/2 + cn/4 + ．．．． = 2cn = o(n)。

为什么分区大小是5而不是3?

如原文所述:

将列表除以5可以保证最坏情况下70−30的分割。至少 至少一半的中位数大于中位数的中位数 n/5块中的一半至少有3个元素，这就给出了a 3n/10的分割，这意味着另一个分区在最坏情况下是7n/10。 得到T(n) = T(n/5)+T(7n/10)+O(n)由于n/5+7n/10 < 1 最差情况运行时间isO(n)。

现在我尝试将上述算法实现为:

public static int findKthLargestUsingMedian(Integer[] array, int k) {
        // Step 1: Divide the list into n/5 lists of 5 element each.
        int noOfRequiredLists = (int) Math.ceil(array.length / 5.0);
        // Step 2: Find pivotal element aka median of medians.
        int medianOfMedian =  findMedianOfMedians(array, noOfRequiredLists);
        //Now we need two lists split using medianOfMedian as pivot. All elements in list listOne will be grater than medianOfMedian and listTwo will have elements lesser than medianOfMedian.
        List<Integer> listWithGreaterNumbers = new ArrayList<>(); // elements greater than medianOfMedian
        List<Integer> listWithSmallerNumbers = new ArrayList<>(); // elements less than medianOfMedian
        for (Integer element : array) {
            if (element < medianOfMedian) {
                listWithSmallerNumbers.add(element);
            } else if (element > medianOfMedian) {
                listWithGreaterNumbers.add(element);
            }
        }
        // Next step.
        if (k <= listWithGreaterNumbers.size()) return findKthLargestUsingMedian((Integer[]) listWithGreaterNumbers.toArray(new Integer[listWithGreaterNumbers.size()]), k);
        else if ((k - 1) == listWithGreaterNumbers.size()) return medianOfMedian;
        else if (k > (listWithGreaterNumbers.size() + 1)) return findKthLargestUsingMedian((Integer[]) listWithSmallerNumbers.toArray(new Integer[listWithSmallerNumbers.size()]), k-listWithGreaterNumbers.size()-1);
        return -1;
    }

    public static int findMedianOfMedians(Integer[] mainList, int noOfRequiredLists) {
        int[] medians = new int[noOfRequiredLists];
        for (int count = 0; count < noOfRequiredLists; count++) {
            int startOfPartialArray = 5 * count;
            int endOfPartialArray = startOfPartialArray + 5;
            Integer[] partialArray = Arrays.copyOfRange((Integer[]) mainList, startOfPartialArray, endOfPartialArray);
            // Step 2: Find median of each of these sublists.
            int medianIndex = partialArray.length/2;
            medians[count] = partialArray[medianIndex];
        }
        // Step 3: Find median of the medians.
        return medians[medians.length / 2];
    }

为了完成，另一种算法利用优先队列，花费时间O(nlogn)。

public static int findKthLargestUsingPriorityQueue(Integer[] nums, int k) {
        int p = 0;
        int numElements = nums.length;
        // create priority queue where all the elements of nums will be stored
        PriorityQueue<Integer> pq = new PriorityQueue<Integer>();

        // place all the elements of the array to this priority queue
        for (int n : nums) {
            pq.add(n);
        }

        // extract the kth largest element
        while (numElements - k + 1 > 0) {
            p = pq.poll();
            k++;
        }

        return p;
    }

这两个算法都可以被测试为:

public static void main(String[] args) throws IOException {
        Integer[] numbers = new Integer[]{2, 3, 5, 4, 1, 12, 11, 13, 16, 7, 8, 6, 10, 9, 17, 15, 19, 20, 18, 23, 21, 22, 25, 24, 14};
        System.out.println(findKthLargestUsingMedian(numbers, 8));
        System.out.println(findKthLargestUsingPriorityQueue(numbers, 8));
    }

如预期输出为: 18 18

还有一种算法，比快速选择算法性能更好。它叫做弗洛伊德-铆钉(FR)算法。

原文:https://doi.org/10.1145/360680.360694

下载版本:http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.309.7108&rep=rep1&type=pdf

维基百科文章https://en.wikipedia.org/wiki/Floyd%E2%80%93Rivest_algorithm

我尝试在c++中实现快速选择和FR算法。我还将它们与标准c++库实现std::nth_element(基本上是quickselect和heapselect的introselect混合)进行了比较。结果是快速选择和nth_element的平均运行，而FR算法的平均运行约。速度是它们的两倍。

我用于FR算法的示例代码:

template <typename T>
T FRselect(std::vector<T>& data, const size_t& n)
{
    if (n == 0)
        return *(std::min_element(data.begin(), data.end()));
    else if (n == data.size() - 1)
        return *(std::max_element(data.begin(), data.end()));
    else
        return _FRselect(data, 0, data.size() - 1, n);
}

template <typename T>
T _FRselect(std::vector<T>& data, const size_t& left, const size_t& right, const size_t& n)
{
    size_t leftIdx = left;
    size_t rightIdx = right;

    while (rightIdx > leftIdx)
    {
        if (rightIdx - leftIdx > 600)
        {
            size_t range = rightIdx - leftIdx + 1;
            long long i = n - (long long)leftIdx + 1;
            long long z = log(range);
            long long s = 0.5 * exp(2 * z / 3);
            long long sd = 0.5 * sqrt(z * s * (range - s) / range) * sgn(i - (long long)range / 2);

            size_t newLeft = fmax(leftIdx, n - i * s / range + sd);
            size_t newRight = fmin(rightIdx, n + (range - i) * s / range + sd);

            _FRselect(data, newLeft, newRight, n);
        }
        T t = data[n];
        size_t i = leftIdx;
        size_t j = rightIdx;
        // arrange pivot and right index
        std::swap(data[leftIdx], data[n]);
        if (data[rightIdx] > t)
            std::swap(data[rightIdx], data[leftIdx]);

        while (i < j)
        {
            std::swap(data[i], data[j]);
            ++i; --j;
            while (data[i] < t) ++i;
            while (data[j] > t) --j;
        }

        if (data[leftIdx] == t)
            std::swap(data[leftIdx], data[j]);
        else
        {
            ++j;
            std::swap(data[j], data[rightIdx]);
        }
        // adjust left and right towards the boundaries of the subset
        // containing the (k - left + 1)th smallest element
        if (j <= n)
            leftIdx = j + 1;
        if (n <= j)
            rightIdx = j - 1;
    }

    return data[leftIdx];
}

template <typename T>
int sgn(T val) {
    return (T(0) < val) - (val < T(0));
}