Super-k: A Piecewise Linear Classifier Based on Voronoi Tessellations
share
Voronoi tessellations are used to partition the Euclidean space into polyhedral regions, which are called Voronoi cells. Labeling the Voronoi cells with the class information, we can map any classification problem into a Voronoi tessellation. In this way, classification problem becomes just finding the enclosing Voronoi cell. In order to accomplish this task, we have developed a new algorithm which generates a labeled Voronoi tessellation that partitions training data into polyhedral regions and obtains interclass boundaries as an indirect result. It is called Supervised k-Voxels or in short Super-k. We are introducing Super-k as a foundational new algorithm and opening the possibility of a new family of algorithms. In this paper, it is shown via comparisons on certain datasets that, the Super-k algorithm has the potential of providing similar accuracy and training performance of the well known SVM family of algorithms with less complexity. Furthermore, the Super-k algorithm has exceptional inference performance. According to the experimental tests the Super-k algorithm is at least 133x faster than the closest competitor.
READ FULL TEXT
