Motivated by the proliferation of machine learning methods in increasingly diverse settings, this workshop aims to bring together researchers and thinkers to reflect upon generalization within all society-facing disciplines and applications of machine learning. We will characterize not just what it means for a machine learning model to do well on future data, but more generally for any entity to behave effectively in unknown future settings. The schedule will complement traditional talks with fireside chats and debates that focus on the future of mathematics and theory in machine learning, and even the general future roles of ML in society.
If you require special accommodation, please contact our access coordinator at simonsevents@berkeley.edu with as much advance notice as possible.