Causality and invariance

• Causal inference using invariant prediction: identification and confidence intervals
• Invariant Risk Minimization
• Conditional variance penalties and domain shift robustness
• Domain Adaptation by Using Causal Inference to Predict Invariant Conditional Distributions

Unifying frameworks

• A Unified Causal View of Domain Invariant Representation Learning
• Invariance Principle Meets Information Bottleneck
• Invariant and Transportable Representations for Anti-Causal Domain Shifts

Empirical work

• Domain-Adjusted Regression or: ERM May Already Learn Features Sufficient for Out-of-Distribution Generalization
• Model Ratatouille: Recycling Diverse Models for Out-of-Distribution Generalization

Perspectives going beyond enforcing conditional independence or invariance

• Probable Domain Generalization via Quantile Risk Minimization
• Iterative Feature Matching: Toward Provable Domain Generalization with Logarithmic Environments
• Domain Generalization using Causal Matching