Skip to yearly menu bar Skip to main content

Workshop: Workshop on Distribution Shifts: Connecting Methods and Applications

Theory and Algorithm for Batch Distribution Drift Problems

Pranjal Awasthi · Corinna Cortes · Christopher Mohri


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.

Chat is not available.