- Alexander Nicholas D'Amour
- Katherine Heller
- Dan Moldovan
- Ben Adlam
- Babak Alipanahi
- Alex Beutel
- Christina Chen
- Jon Deaton
- Jacob Eisenstein
- Matthew D. Hoffman
- Farhad Hormozdiari
- Shaobo Hou
- Neil Houlsby
- Ghassen Jerfel
- Alan Karthikesalingam
- Mario Lučić
- Yian Ma
- Cory McLean
- Diana Mincu
- Akinori Mitani
- Andrea Montanari
- Zachary Nado
- Vivek Natarajan
- Christopher Nielsen
- Thomas Osborne
- Rajiv Raman
- Kim Ramasamy
- Rory Abbott Sayres
- Jessica Schrouff
- Martin Gamunu Seneviratne
- Shannon Sequeira
- Harini Suresh
- Victor Veitch
- Max Vladymyrov
- Xuezhi Wang
- Kellie Webster
- Steve Yadlowsky
- Taedong Yun
- Xiaohua Zhai
- D. Sculley
Abstract
ML models often exhibit unexpectedly poor behavior when they are deployed in real-world domains. We identify underspecification as a key reason for these failures. An ML pipeline is underspecified when it can return many predictors with equivalently strong held-out performance in the training domain. Underspecification is common in modern ML pipelines, such as those based on deep learning. Predictors returned by underspecified pipelines are often treated as equivalent based on their training domain performance, but we show here that such predictors can behave very differently in deployment domains. This ambiguity can lead to instability and poor model behavior in practice, and is a distinct failure mode from previously identified issues arising from structural mismatch between training and deployment domains. We show that this problem appears in a wide variety of practical ML pipelines, using examples from computer vision, medical imaging, natural language processing, clinical risk prediction based on electronic health records, and medical genomics. Our results show the need to explicitly account for underspecification in modeling pipelines that are intended for real-world deployment in any domain.
Research Areas
Learn more about how we do research
We maintain a portfolio of research projects, providing individuals and teams the freedom to emphasize specific types of work