A Parallel Algorithms on Nearest Neighbor Search

The (k-)nearest neighbor searching has very high computational costs. The algorithms presented for nearest neighbor search in high dimensional spaces have have suffered from curse of dimensionality, which affects either runtime or storage requirements of the algorithms terribly. Parallelization of nearest neighbor search is a suitable solution for decreasing the workload caused by nearest neighbor searching in high dimensions. In this paper, we have surveyed notable advancements in the parallelization efforts on nearest neighbor searching algorithms. The algorithms covered are ordered chronologically for exhibiting the evolution throughout the years. Recent improvements on GPU based nearest neighbor search algorithms are covered. Additionally, we address the open problems in the area of parallel nearest neighbor algorithms.