About the project
Distribution shift between training and test data has been a major challenge for decades. For instance, scarce disease data for training and test in a local hospital can be different. We focus on the overall generalization performance on multiple clients and modify the classical ERM to obtain an unbiased estimate of an overall true risk minimizer under intra-client and inter-client distribution shifts, develop an efficient density ratio estimation method under stringent privacy requirements of federated learning, and show importance-weighted ERM achieves smaller generalization error than classical ERM.
Project team
-
Associate Professor Ali Ramezani-Kebrya, University of Oslo, Department of Informatics
-
Professor Robert Jenssen, UiT The Arctic University of Norway, Department of Physics and Technology
-
PhD Fellow Zhiyuan Wu, University of Oslo, Department of Informatics
-
Postdoctoral Fellow Changkyu Choi, UiT The Arctic University of Norway, Department of Physics and Technology