Causality-oriented robustness: exploiting general noise interventions

Understand

Since distribution shifts are common in real-world applications, there is a pressing need to develop prediction models that are robust against such shifts.

• Existing frameworks, such as empirical risk minimization or distributionally robust optimization, either lack generalizability for unseen distributions or rely on postulated distance measures.
• Alternatively, causality offers a data-driven and structural perspective to robust predictions.
• However, the assumptions necessary for causal inference can be overly stringent, and the robustness offered by such causal models often lacks flexibility.