Benchmark shows new e-means clustering 100x slower than Lance's hierarchical k-means

leland_mcinnes · x · 2026-11-17

FAISS recently shipped e-means, claiming it beats k-means with 10x fewer epochs. A quick benchmark by changhiskhan's team tells a different story.

Takeaway: on real large-scale data, classic hierarchical k-means remains dramatically faster, and e-means's claimed speedups did not reproduce.

Original post →

More from Infra

Infra channel →