A sub-linear time algorithm for approximating k-nearest-neighbor with full quality guarantee

• We propose an algorithm that unifies the distance and recall criteria for approximate k-Nearest-Neighbor problem. The is first one studied problem provides theoretical guarantee on both approximation criteria. achieves sub-linear query time while providing guarantees. In this paper we k-Nearest-Neighbors According to existing researches, there are two kinds of One criterion, other criterion. All former algorithms suffer no guarantees proposed in criteria, has full Furthermore, sub-linear. As far as know, it guarantee.