Classification in asymmetric spaces via sample compression
This addresses classification problems in asymmetric spaces, which is a novel theoretical extension but likely incremental in practical impact.
The paper tackled classification in quasi-metric spaces, which are asymmetric distance spaces, by developing a learning algorithm based on sample compression and nearest neighbor methods, and proved it has favorable statistical properties.
We initiate the rigorous study of classification in quasi-metric spaces. These are point sets endowed with a distance function that is non-negative and also satisfies the triangle inequality, but is asymmetric. We develop and refine a learning algorithm for quasi-metrics based on sample compression and nearest neighbor, and prove that it has favorable statistical properties.