Uri Shalit is assistant professor in the Faculty of Data and Decision Sciences at the Technion, Israel and he will present work showing how a robust notion of model calibration ties into the idea of invariant learning, and leads to models that can generalize out-of-domain (OOD) in both theory and practice.
Overview
- Date:Starts 9 March 2023, 13:00Ends 9 March 2023, 14:00
- Location:Analysen, EDIT-building and zoom
- Language:English
Uri Shalit will then show how practical difficulties with optimizing the above models lead us to a new result with ramifications for OOD generalization, fairness and robustness: We prove how “benign overfitting”, where deep models interpolate the training set yet generalize well, can be fundamentally at odds with learning invariant models.
Short bio
Uri Shalit is assistant professor in the Faculty of Data and Decision Sciences at the Technion, Israel. Uri directs the Machine Learning & Causal Inference in Healthcare Lab who work on developing new methods for using data in decision making with machine learning and causal inference.
The seminar is hybrid zoom-link, password: mondays23
- Visiting Researcher, Data Science and AI, Computer Science and Engineering