Two Counterexamples for e-means
e-means (Bessa et al., 2026) combines exponential averaging and cluster revival. We give two counterexamples to its published recipe with higher final loss than standard k-means (Lloyd, 1982) from identical initial centers. Mass-based revival can destroy a global optimum and make the ratio of expected losses unbounded even with k-means++ seeding.
Authors
- Zhenisbek Assylbekov (ORCID: https://orcid.org/0000-0003-0095-9409)
Publication Details
- Journal
- arXiv (Cornell University)
- Published
- 2026-11-17
- DOI
- https://doi.org/10.48550/arxiv.2611.22065
- Primary Topic
- Advanced Clustering Algorithms Research
- Type
- preprint