Importance Tempering: Group Robustness for Overparameterized Models
This addresses robustness issues for overparameterized models in real-world applications, representing a novel method for a known bottleneck.
The paper tackles the problem of accuracy drop in overparameterized models under distribution shifts by proposing importance tempering, achieving state-of-the-art results on worst group classification tasks.
Although overparameterized models have shown their success on many machine learning tasks, the accuracy could drop on the testing distribution that is different from the training one. This accuracy drop still limits applying machine learning in the wild. At the same time, importance weighting, a traditional technique to handle distribution shifts, has been demonstrated to have less or even no effect on overparameterized models both empirically and theoretically. In this paper, we propose importance tempering to improve the decision boundary and achieve consistently better results for overparameterized models. Theoretically, we justify that the selection of group temperature can be different under label shift and spurious correlation setting. At the same time, we also prove that properly selected temperatures can extricate the minority collapse for imbalanced classification. Empirically, we achieve state-of-the-art results on worst group classification tasks using importance tempering.