Robust Generalization despite Distribution Shift via Minimum Discriminating Information

Author name not available (Why is that?)

Publication date: 8 June 2021

Abstract: Training models that perform well under distribution shifts is a central challenge in machine learning. In this paper, we introduce a modeling framework where, in addition to training data, we have partial structural knowledge of the shifted test distribution. We employ the principle of minimum discriminating information to embed the available prior knowledge, and use distributionally robust optimization to account for uncertainty due to the limited samples. By leveraging large deviation results, we obtain explicit generalization bounds with respect to the unknown shifted distribution. Lastly, we demonstrate the versatility of our framework by demonstrating it on two rather distinct applications: (1) training classifiers on systematically biased data and (2) off-policy evaluation in Markov Decision Processes.

Has companion code repository: https://github.com/tobsutter/pmdi_dro

This page was built for publication: Robust Generalization despite Distribution Shift via Minimum Discriminating Information

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6369773)