Benchmark of Approximate Nearest Neighbor libraries

1 · Erik Bernhardsson · July 4, 2015, 4 a.m.
Annoy is a library written by me that supports fast approximate nearest neighbor queries. Say you have a high (1-1000) dimensional space with points in it, and you want to find the nearest neighbors to some point. Annoy gives you a way to do this very quickly. It could be points on a map, but also word vectors in a latent semantic representation or latent item vectors in collaborative filtering. I’ve made a few optimizations to Annoy lately and I was curious to see how it stacks up against other...