Learning by Conformal Predictors with Additional Information

Abstract

In many supervised learning applications, the existence of additional information in training data is very common. Recently, Vapnik introduced a new method called LUPI which provides a learning paradigm under privileged (or additional) information. It describes the SVM+ technique to process this information in batch mode. Following this method, we apply the approach to deal with additional information by conformal predictors. An application to a medical diagnostic problem is considered and the results are reported.

Conformal Prediction under Probabilistic Input

“…This task is equivalent to learning under privileged (additional) information framework formulated in [4]. The conformal approach of this task was developed in the work [5]. An analogue of credibility was assigned to the sequence…”

“…Another kind of the task is Vapnik's Learning under privileged information [4] that can be interpreted as having missing values in testing examples. A conformal approach to it was made in the work [5].…”