微软 data & applied scientist 电面+onsite

Phone interview (30 mins)
Brief explain your experience and elaborate one project
K-means clustering (explain the algorithm in detail; whether it will converge, global or local optimums; when k-means will converge and how to stop; etc)
Given a m*n matrix, going from left upper to right lower corner, you can only go right or go down. How many possible paths are there? Answer: m+n choose n


Onsite interview (4 rounds)
1. Talk about one of my projects in tons of details

您好！
本帖隐藏的内容需要积分高于 200 才可浏览
您当前积分为 0。
使用VIP即刻解锁阅读权限或查看其他获取积分的方式

游客，您好！
本帖隐藏的内容需要积分高于 200 才可浏览
您当前积分为 0。
VIP即刻解锁阅读权限 或 查看其他获取积分的方式
Unlock interview details and practice with AI
Curated Interview Questions from Top Companies

how to sample (consider power law distribution) 不太看得懂啥意思

time complexity应该是nlog(k)吧？by the way, 没看懂followup (given a O(N) algorithm that returns the index of element in sorted array, what's its time complexity to find k th largest number)

想问一下kmeans clustering 怎么处理cluster很大或很小的问题呀？ 楼主是怎么回答的？ 已加米

楼主有收到消息吗

下周有面试 想知道楼主可不可以私信一下内容 看不到因为米不够

大米不够😭楼主可不可以私信一下内容

感谢楼主分享内容，虽然目前还看不到，留言MARK一下

大米不够😔

大米不够😭楼主可不可以私信一下内容