Learning Partition Trees for Nearest Neighbor SearchResearch Paper
Nearest neighbor search asks for a data structure on a dataset of points that, given a query , returns a point of closest to . In high dimension, worst-case guarantees are known only with a multiplicative approximation to the distance (Andoni, Indyk 2006; Andoni, Laarhoven, Razenshteyn, Waingarten 2017). Practical systems are…