Efficient nearest neighbor classification with data reduction and fast search algorithms

The nearest neighbor classifier is one of the most popular non-parametric classification methods. It is very simple, intuitive and accurate in a great variety of real-world applications. Despite its simplicity and effectiveness, practical use of this decision rule has been historically limited due to its high storage requirements and the computational costs involved. In order to overcome these drawbacks, it is possible either to employ fast search algorithms or to use training set size reduction scheme. The present paper provides a comparative analysis of fast search algorithms and data reduction techniques to assess their pros and cons from both theoretical and practical viewpoints