A1155
Title: Distributionally robust invariance learning for domain generalization and adaptation
Authors: Peter Buehlmann - ETH Zurich (Switzerland) [presenting]
Abstract: Statistical models and machine learning systems are increasingly deployed in populations and settings that differ from those on which they were trained, a challenge that is especially pronounced in digital health. Distributionally Robust Invariance Learning is introduced, a framework designed to identify and exploit stable structure across heterogeneous environments. Its use is illustrated for domain generalization and domain adaptation using a large-scale international intensive care unit (ICU) database spanning multiple countries. A discussion of the opportunities and limitations of emerging foundation models in this setting is provided.
