A Note on Approximate Nearest Neighbor Methods
Information Retrieval
2007-05-23 v1 Computational Complexity
Computer Vision and Pattern Recognition
Abstract
A number of authors have described randomized algorithms for solving the epsilon-approximate nearest neighbor problem. In this note I point out that the epsilon-approximate nearest neighbor property often fails to be a useful approximation property, since epsilon-approximate solutions fail to satisfy the necessary preconditions for using nearest neighbors for classification and related tasks.
Cite
@article{arxiv.cs/0703101,
title = {A Note on Approximate Nearest Neighbor Methods},
author = {Thomas M. Breuel},
journal= {arXiv preprint arXiv:cs/0703101},
year = {2007}
}
Comments
The report was originally written in 2005 and does not reference information after that date