Generalization error bounds for the logical analysis of data

This paper analyzes the predictive performance of standard techniques for the 'logical analysis of data' (LAD), within a probabilistic framework. We bound the generalization error of classifiers produced by standard LAD methods in terms of their complexity and how well they fit the training data. We also quantify the predictive accuracy in terms of the extent to which the underlying LAD discriminant function achieves a large separation (a 'large margin') between (most of) the positive and negative observations