Zero-error dissimilarity based classifiers
This work addresses classification challenges for real-world objects represented by distances, but it appears incremental as it builds on existing dissimilarity-based methods without claiming broad breakthroughs.
The paper tackles the problem of classifying objects using non-Euclidean distance measures, deriving conditions for zero-error classifiers and ensuring the decision boundary is a continuous function of distances to training samples, with practical applicability argued.
We consider general non-Euclidean distance measures between real world objects that need to be classified. It is assumed that objects are represented by distances to other objects only. Conditions for zero-error dissimilarity based classifiers are derived. Additional conditions are given under which the zero-error decision boundary is a continues function of the distances to a finite set of training samples. These conditions affect the objects as well as the distance measure used. It is argued that they can be met in practice.