Wednesday, November 11, 2026Nov 11RSSby nabulinesFollow @nabu_lines
Releases

Meta researchers propose e-means, a faster upgrade to k-means

The method needs about a tenth of the training passes with lower error.

945Releases
Image from the post by @askalphaxiv on X: Meta researchers propose e-means, a faster upgrade to k-means
Image from the original post by @askalphaxiv on X

alphaXiv (@askalphaxiv) highlighted a paper from Meta researchers proposing e-means, which outperforms k-means with about 1/10 the training passes and lower clustering error.

It updates cluster centers with smaller batches and exponential moving averages, and uses scaling laws to pick batch size and learning rate. The post says it reaches lower error in 1.4-2.6 epochs versus 25 for k-means, with 10-45x GPU speedups, and can cluster 10 billion embeddings into 16 million groups in 2.5 epochs.

Why it mattersK-means is one of the most used algorithms in ML.

The post drew about 515 likes by Wednesday morning.

More from Nov 11, 2026

Full roundup →
The daily brief · coming soon

Five minutes. Every story that mattered.

One email each morning with the AI, crypto and tech posts everyone is talking about, explained in plain English.

Launching soon. No spam, unsubscribe anytime. Follow @nabu_lines meanwhile.