A Framework for Structural Risk Minimisation Produced as Part of the Esprit Working Group in Neural and Computational Learning, Neurocolt 8556

The paper introduces a framework for studying structural risk minimi-sation. The model views structural risk minimisation in a PAC context. It then considers the more general case when the hierarchy of classes is chosen in response to the data. This theoretically explains the impressive performance of the maximal margin hyperplane algorithm of Vapnik. It may also provide a general technique for exploiting serendipitous simplicity in observed data to obtain better prediction accuracy from small training sets.