A discrete mathematics approach for large scale improvement in classification training time

Abstract

A scalable graphical method is presented for selecting datasets for the training phase of a classification task. For the heuristic, a clustering algorithm is required to get its computation cost in a reasonable proportion to the task itself. This step is succeeded by construction of an information graph of the underlying classification patterns using approximate nearest neighbor methods. Lastly, the information graph is used for reducing a given training set. The heuristic targets large datasets, since the primary goal is a significant reduction in training computation run-time without compromising prediction accuracy. Test results show that the approach significantly speedup the training task when compared against that of state-of the-art shrinking heuristics available in LIBSVM. Furthermore, the approaches closely follow or even outperform in prediction accuracy.