Robust Learning in Heterogeneous Contexts
This work addresses robust learning in heterogeneous contexts, which is an incremental improvement over existing methods like minimax approaches.
The paper tackles the problem of learning from training data with unknown context distributions by developing a robust method that accounts for distribution uncertainty, achieving a trade-off between performance and robustness without harming nominal performance.
We consider the problem of learning from training data obtained in different contexts, where the underlying context distribution is unknown and is estimated empirically. We develop a robust method that takes into account the uncertainty of the context distribution. Unlike the conventional and overly conservative minimax approach, we focus on excess risks and construct distribution sets with statistical coverage to achieve an appropriate trade-off between performance and robustness. The proposed method is computationally scalable and shown to interpolate between empirical risk minimization and minimax regret objectives. Using both real and synthetic data, we demonstrate its ability to provide robustness in worst-case scenarios without harming performance in the nominal scenario.