Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization
This addresses the reliability of machine learning systems for practitioners by providing empirical evidence on generalization correlations, though it is incremental as it builds on existing domain adaptation theory.
The paper tackles the problem of understanding machine learning reliability by empirically showing that out-of-distribution performance is strongly correlated with in-distribution performance across various models and distribution shifts, with strong correlations observed on datasets like CIFAR-10, ImageNet, and WILDS benchmarks, and it investigates weaker correlation cases such as CIFAR-10-C and Camelyon17-WILDS.
For machine learning systems to be reliable, we must understand their performance in unseen, out-of-distribution environments. In this paper, we empirically show that out-of-distribution performance is strongly correlated with in-distribution performance for a wide range of models and distribution shifts. Specifically, we demonstrate strong correlations between in-distribution and out-of-distribution performance on variants of CIFAR-10 & ImageNet, a synthetic pose estimation task derived from YCB objects, satellite imagery classification in FMoW-WILDS, and wildlife classification in iWildCam-WILDS. The strong correlations hold across model architectures, hyperparameters, training set size, and training duration, and are more precise than what is expected from existing domain adaptation theory. To complete the picture, we also investigate cases where the correlation is weaker, for instance some synthetic distribution shifts from CIFAR-10-C and the tissue classification dataset Camelyon17-WILDS. Finally, we provide a candidate theory based on a Gaussian data model that shows how changes in the data covariance arising from distribution shift can affect the observed correlations.