Automatic, Debiased, and Invariant Counterfactual Generation under General Interventions
This work addresses the need for reliable counterfactual generation in decision-making under complex interventions, offering theoretical guarantees for robustness and invariance.
ADIGen introduces a framework for counterfactual generation under general interventions that avoids unstable density-ratio estimation, improves generalization under distribution shift, and provides doubly robust guarantees against nuisance model misspecification, with theoretical excess-risk bounds.
Generative models for counterfactual outcomes have great potential to support decision-making under complex interventions, but existing approaches are limited by unstable estimation, poor generalization across environments, and bias from nuisance model misspecification. We introduce ADIGen, a framework for automatic, debiased, and invariant counterfactual generation under general interventions, including high-dimensional interventions and outcomes. ADIGen combines Riesz regression to avoid unstable density-ratio estimation, causal invariance to improve generalization under distribution shift, and orthogonal statistical learning to obtain doubly robust guarantees against nuisance model misspecification. We provide excess-risk bounds showing that ADIGen controls counterfactual risk under general interventions, with a product-bias nuisance remainder and an invariant risk bound across environments.