Modeling the Q-Diversity in a Min-max Play Game for Robust Optimization
Modeling the Q-Diversity in a Min-max Play Game for Robust Optimization
Models trained with empirical risk minimization (ERM) are revealed to easily rely on spurious correlations, resulting in poor generalization. Group distributionally robust optimization (group DRO) can alleviate this problem by minimizing the worst-case loss over pre-defined groups. While promising, in practice factors like expensive annotations and privacy preclude the availability …