Learning Under Persistent Drift

In this paper we study learning algorithms for environments which are changing over time. Unlike most previous work, we are interested in the case where the changes might be rapid but their “direction” is relatively constant. We model this type of change by assuming that the target distribution is changing continuously at a constant rate from one extreme distribution to another. We show in this case how to use a simple weighting scheme to estimate the error of an hypothesis, and using this estimate, to minimize the error of the prediction.