Underspecification Presents Challenges for Credibility in Modern Machine Learning
Abstrak
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.
Topik & Kata Kunci
Penulis (40)
A. D'Amour
K. Heller
D. Moldovan
Ben Adlam
Babak Alipanahi
Alex Beutel
Christina Chen
Jonathan Deaton
Jacob Eisenstein
M. Hoffman
F. Hormozdiari
N. Houlsby
Shaobo Hou
Ghassen Jerfel
A. Karthikesalingam
M. Lučić
Yi-An Ma
Cory Y. McLean
Diana Mincu
A. Mitani
A. Montanari
Zachary Nado
Vivek Natarajan
Christopher Nielson
Thomas F. Osborne
R. Raman
K. Ramasamy
R. Sayres
Jessica Schrouff
Martin G. Seneviratne
Shannon Sequeira
Harini Suresh
Victor Veitch
Max Vladymyrov
Xuezhi Wang
Kellie Webster
Steve Yadlowsky
T. Yun
Xiaohua Zhai
D. Sculley
Akses Cepat
PDF tidak tersedia langsung
Cek di sumber asli →- Tahun Terbit
- 2020
- Bahasa
- en
- Total Sitasi
- 825×
- Sumber Database
- Semantic Scholar
- Akses
- Open Access ✓