Monday, January 29, 2024 — 10:00 AM to 1:00 PM EST
Please note: This PhD defence will take place in DC 3317 and online.
Nils Lukas, PhD candidate
David R. Cheriton School of Computer Science
Supervisor: Professor Florian Kerschbaum
Monday, January 29, 2024 — 10:30 AM to 11:30 AM EST
Please note: This seminar will take place in DC 1304.
Shiori Sagawa, PhD candidate
Department of Computer Science, Stanford University
Machine learning systems are powerful, but they can fail due to distribution shifts: mismatches in the data distribution between training and deployment. Distribution shifts are ubiquitous and have real-world consequences: models can fail on subpopulations (e.g., demographic groups) and on new domains unseen during training (e.g., new hospitals).
