Nearly-Tight and Oblivious Algorithms for Explainable Clustering

no code implementations • NeurIPS 2021 • Buddhima Gamlath, Xinrui Jia, Adam Polak, Ola Svensson

We give an algorithm that outputs an explainable clustering that loses at most a factor of $O(\log^2 k)$ compared to an optimal (not necessarily explainable) clustering for the $k$-medians objective, and a factor of $O(k \log^2 k)$ for the $k$-means objective.

Clustering