On the Current State of Research in Explaining Ensemble Performance Using Margins

Other authors suggest that specific margin instances Forests (Breiman, 2001) and rotation forests (Rodriguez hold a clue to better generalization (Shen and Li, et al., 2006), create a set of weak classifiers from 2010; Wang et al., 2011, 2012). In this article, we design a base learning algorithm B, which are typically decision algorithms to empirically test whether the state of research trees, then combine the predictions from the classifiers in in the explanation of ensemble performance translates into the form of a weighted vote, to produce an improved prediction better performing algorithms. We do not question the theoretical compared to individual classifiers (Drucker et al., soundness of the generalization error bounds, but 1994; Dietterich, 2000; Breiman, 2001; Maclin and Opitz, simply test whether evidence suggests that better performing 2011). Upper bounds based on the sample margins of the ensemble algorithms can be derived from the practical ensemble provide some explanation on why ensembles perform interpretations of the bounds. In the next section we discuss as well as they do. Schapire et al. (1998) first pointed margins, the generalization error bounds based on the to margins as a key determinant of ensemble performance.