Impossibility of Depth Reduction in Explainable Clustering

no code implementations • 4 May 2023 • Chengyuan Deng, Surya Teja Gavva, Karthik C. S., Parth Patel, Adarsh Srinivasan

Formally, we show that there exists a data set X in the Euclidean plane, for which there is a decision tree of depth k-1 whose k-means/k-median cost matches the optimal clustering cost of X, but every decision tree of depth less than k-1 has unbounded cost w. r. t.

Clustering