Robust Supervised Learning

Abstract

Supervised machine learning techniques developed in the Probably Approximately Correct, Maximum A Posteriori, and Structural Risk Minimization Frameworks typically make the assumption that the test data a learner is applied to is drawn from the same distribution as the training data. In various prominent applications of learning techniques, from robotics to medical diagnosis, this assumption is violated. We consider a novel framework where a learner influence the test distribution in a bounded way. From this framework, we derive an efficient algorithm that acts as a wrapper around a broad class of existing supervised learning techniques while guarranteeing more robst behavior under changes in input distribution.