English

The computational complexity of some explainable clustering problems

Machine Learning 2022-08-23 v1 Data Structures and Algorithms

Abstract

We study the computational complexity of some explainable clustering problems in the framework proposed by [Dasgupta et al., ICML 2020], where explainability is achieved via axis-aligned decision trees. We consider the kk-means, kk-medians, kk-centers and the spacing cost functions. We prove that the first three are hard to optimize while the latter can be optimized in polynomial time.

Keywords

Cite

@article{arxiv.2208.09643,
  title  = {The computational complexity of some explainable clustering problems},
  author = {Eduardo Sany Laber},
  journal= {arXiv preprint arXiv:2208.09643},
  year   = {2022}
}

Comments

14 pages and 1 figure

R2 v1 2026-06-25T01:50:14.587Z