Minimum Risk Feature Transformations

We develop an approach for automatically learning the optimal feature transformation for a given classification problem. The approach is based on extending the principle of risk minimization (RM), commonly used for learning classifiers, to learning feature transformations that admit classifiers with minimum risk. This allows feature extraction and classification to proceed in a unified framework, both guided by the RM principle. The framework is applied to derive new algorithms for learning feature transformations. Our experiments demonstrate the ability of the resulting algorithms to learn good features for a variety of classification problems.