đź“„ Paper accepted at AISTATS 2025
Description
The term diluted causality comes from Bühlmann (2018), inspired by a suggestion from Edward George. It reflects the notion that while causal mechanisms are expected to be invariant under all possible interventions, a weaker form of invariance—diluted causality—can be more desirable in practice. This weaker notion restricts the set of interventions to those most relevant for predictive generalisation.
This project investigates the interplay between causality, invariance, and out-of-distribution (OOD) generalisation. It builds upon influential work by Peter Bühlmann, Nicolai Meinshausen, Jonas Peters, Dominik Rothenhäusler, Rune Christiansen, and others.
We especially recommend reviewing these foundational papers to understand the core concepts connecting causality and robustness:
- Peters et al. (2016) – Causal Inference by Using Invariant Prediction: Identification and Confidence Intervals
- Bühlmann (2018) – Invariance, Causality and Robustness
- Meinshausen (2018) – Causality from a Distributional Robustness Point of View
- Rothenhäusler et al. (2021) – Anchor Regression: Heterogeneous Data Meet Causality
- Christiansen et al. (2022) – A Causal Framework for Distribution Generalization
- Jakobsen et al. (2022) – Distributional Robustness of K-Class Estimators and the PULSE
This project offers a concise introduction to this learning framework and highlights our contribution to the field. For a quick primer, check out the following:
👉 Introduction to out-of-distribution generalization from a causal perspective