Skip to yearly menu bar Skip to main content


Improved Guarantees for k-means++ and k-means++ Parallel

Konstantin Makarychev · Aravind Reddy · Liren Shan

Poster Session 4 #1178


In this paper, we study k-means++ and k-means||, the two most popular algorithms for the classic k-means clustering problem. We provide novel analyses and show improved approximation and bi-criteria approximation guarantees for k-means++ and k-means||. Our results give a better theoretical justification for why these algorithms perform extremely well in practice.

Chat is not available.