Randomized partition trees for exact nearest neighbor search

Abstract

The k-d tree was one of the first spatial data structures proposed for nearest neighbor search. Its efficacy is diminished in high-dimensional spaces, but several variants, with randomization and overlapping cells, have proved to be successful in practice. We analyze three such schemes. We show that the probability that they fail to find the nearest neighbor, for any data set and any query point, is directly related to a simple potential function that captures the difficulty of the point configuration. We then bound this potential function in two situations of interest: the first, when data come from a doubling measure, and the second, when the data are documents from a topic model.

Cited by in corpus (9)

• Nonparametric Conditional Density Estimation in a High-Dimensional Regression Setting
• Learning Space Partitions for Nearest Neighbor Search
• Towards Similarity Graphs Constructed by Deep Reinforcement Learning
• Sparse Projection Oblique Randomer Forests
• Selecting the independent coordinates of manifolds with large aspect ratios
• Adaptive Non-Parametric Regression With the $K$-NN Fused Lasso
• Distributed Nearest Neighbor Classification
• Nearest Neighbor Search Under Uncertainty
• IRLI: Iterative Re-partitioning for Learning to Index