ANNS – Approximate Nearest Neighbor Search – a method of finding the nearest neighbor of a given query point in a large dataset of points using various approximate nearest neighbor algorithms. ANNS aims to find an approximate nearest neighbor with high probability while minimizing the computational cost. It navigates the search space to locate approximate matches efficiently, significantly improving performance compared to exhaustive searches.
The standard nearest neighbor search (NN search) algorithm is an exhaustive search that checks the distance between the query point and every other point in the dataset. This can be computationally expensive and infeasible for large datasets.
ANMS operates within a vector space; a mathematical representation of high-dimensional data used to perform similarity searches. ANN algorithms, such as locality-sensitive hashing (LSH) and KD-trees, were designed to efficiently search for approximate nearest neighbors in high-dimensional spaces.
A Zilliz glossary entry, which we have used, has more information, as does an Elastic webpage.
