New Hartigan k-means variant improves clustering results by up to 10%

By PulseAugur Editorial · [1 sources] · 2026-04-23 15:57

Researchers have developed an improved version of the Hartigan k-means clustering algorithm, building upon its known advantages over Lloyd's algorithm. This minor variation reportedly yields an additional 2-5% improvement in clustering results, with the gains becoming more pronounced as the dimensionality or number of clusters increases. AI

IMPACT Minor algorithmic refinement for clustering; unlikely to significantly impact broad AI applications.

RANK_REASON Academic paper detailing an algorithmic improvement.

Read on arXiv cs.LG →

paper
other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

COVERAGE [1]

arXiv cs.LG TIER_1 English(EN) · Stefan Steinerberger · 2026-04-23 15:57

An effective variant of the Hartigan $k$-means algorithm

The k-means problem is perhaps the classical clustering problem and often synonymous with Lloyd's algorithm (1957). It has become clear that Hartigan's algorithm (1975) gives better results in almost all cases, Telgarsky-Vattani note a typical improvement of $5\%$ -- $10\%$. We p…

COVERAGE [1]

An effective variant of the Hartigan $k$-means algorithm

RELATED TOPICS