Influence of Machine Learning vs. Ranking Algorithm on the Critical Dimension

The critical dimension is the minimum number of features required for a learning machine to perform with “high” accuracy, which for a specific dataset is dependent upon the learning machine and the ranking algorithm. Discovering the critical dimension, if one exists for a dataset, can help to reduce the feature size while maintaining the learning machine’s performance. It is important to understand the influence of learning machines and ranking algorithms on critical dimension to reduce the feature size effectively. In this paper we experiment with three ranking algorithms and three learning machines on several datasets to study their combined effect on the critical dimension. Results show the ranking algorithm has greater influence on the critical dimension than the learning machine.