Timezone: »

Estimating Generalization under Distribution Shifts via Domain-Invariant Representations
Ching-Yao Chuang · Antonio Torralba · Stefanie Jegelka

Tue Jul 14 03:00 PM -- 03:45 PM & Wed Jul 15 04:00 AM -- 04:45 AM (PDT) @ None #None

When machine learning models are deployed on a test distribution different from the training distribution, they can perform poorly, but overestimate their performance. In this work, we aim to better estimate a model's performance under distribution shift, without supervision. To do so, we use a set of domain-invariant predictors as a proxy for the unknown, true target labels. Since the error of the resulting risk estimate depends on the target risk of the proxy model, we study generalization of domain-invariant representations and show that the complexity of the latent representation has a significant influence on the target risk. Empirically, our approach (1) enables self-tuning of domain adaptation models, and (2) accurately estimates the target error of given models under distribution shift. Other applications include model selection, deciding early stopping and error detection.

Author Information

Ching-Yao Chuang (MIT)
Antonio Torralba (MIT)
Stefanie Jegelka (Massachusetts Institute of Technology)

More from the Same Authors