The Canonical Distortion Measure in Feature Space and 1-NN Classification
Abstract
We prove that the Canonical Distortion Measure (CDM) [2, 3] is the optimal distance measure to use for I nearest-neighbour (l-NN) classifi(cid:173) cation, and show that it reduces to squared Euclidean distance in feature space for function classes that can be expressed as linear combinations of a fixed set of features. PAC-like bounds are given on the sample(cid:173) complexity required to learn the CDM. An experiment is presented in which a neural network CDM was learnt for a Japanese OCR environ(cid:173) ment and then used to do I-NN classification.
Cite
Text
Baxter and Bartlett. "The Canonical Distortion Measure in Feature Space and 1-NN Classification." Neural Information Processing Systems, 1997.Markdown
[Baxter and Bartlett. "The Canonical Distortion Measure in Feature Space and 1-NN Classification." Neural Information Processing Systems, 1997.](https://mlanthology.org/neurips/1997/baxter1997neurips-canonical/)BibTeX
@inproceedings{baxter1997neurips-canonical,
title = {{The Canonical Distortion Measure in Feature Space and 1-NN Classification}},
author = {Baxter, Jonathan and Bartlett, Peter L.},
booktitle = {Neural Information Processing Systems},
year = {1997},
pages = {245-251},
url = {https://mlanthology.org/neurips/1997/baxter1997neurips-canonical/}
}