The Canonical Distortion Measure in Feature Space and 1-NN Classification
Baxter, Jonathan, Bartlett, Peter L.
–Neural Information Processing Systems
We prove that the Canonical Distortion Measure (CDM) [2, 3] is the optimal distance measure to use for I nearest-neighbour (l-NN) classification, andshow 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.
Neural Information Processing Systems
Dec-31-1998