Theory and Algorithm for Batch Distribution Drift Problems

We study a problem of gradual \emph{batch distribution drift} motivated by several applications, which consists of determining an accurate predictor for a target time segment, for which a moderate amount of labeled samples are at one's disposal, while leveraging past segments for which substantially more labeled samples are available. We give new algorithms for this problem guided by a new theoretical analysis and generalization bounds derived for this scenario. Additionally, we report the results of extensive experiments demonstrating the benefits of our drifting algorithm, including comparisons with natural baselines.