Get the latest tech news

SuperEMeans: Making e-means 3× faster


TL;DR: We fused SuperKMeans and e-means, resulting in 3× faster clustering of high-dimensional vectors without quality trade-offs. Available now at https://github.com/cwida/SuperKMeans. Recently, there has been a lot of buzz around clustering of vector embeddings: EVōC, SuperKMeans, QGKmeans, and just last week, e-means, o-means, and s-means. Among these, e-means is a big deal: it promises the same quality as Lloyd’s with only 2 epochs. Why is this a big deal for vector search? Well, clustering is a key building block for large-scale vector indexes (e.g., IVF, ScANN), which is precisely the bottleneck that users have to wait on before issuing similarity search queries.

None

Get the Android app

Or read this on Hacker News

Read more on:

Photo of SuperEMeans

SuperEMeans