Classification by discriminative regularization

Abstract

Classification is one of the most fundamental problems in machine learning, which aims to separate the data from different classes as far away as possible. A common way to get a good classification function is to minimize its empirical prediction loss or structural loss. In this paper, we point out that we can also enhance the discriminality of those classifiers by further incorporating the discriminative information contained in the data set as a prior into the classifier construction process. In such a way, we will show that the constructed classifiers will be more powerful, and this will also be validated by the final empirical study on several benchmark data sets. Copyright © 2008, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.