DoubleGen: Debiased Generative Modeling of Counterfactuals
This addresses bias in counterfactual modeling for causal inference, offering a robust solution with theoretical guarantees, though it is incremental in applying doubly robust methods to generative models.
The paper tackled bias in generative models for counterfactual outcomes by introducing DoubleGen, a doubly robust framework that mitigates confounding and misspecification biases, achieving oracle optimality and minimax rate optimality with finite-sample guarantees.
Generative models for counterfactual outcomes face two key sources of bias. Confounding bias arises when approaches fail to account for systematic differences between those who receive the intervention and those who do not. Misspecification bias arises when methods attempt to address confounding through estimation of an auxiliary model, but specify it incorrectly. We introduce DoubleGen, a doubly robust framework that modifies generative modeling training objectives to mitigate these biases. The new objectives rely on two auxiliaries -- a propensity and outcome model -- and successfully address confounding bias even if only one of them is correct. We provide finite-sample guarantees for this robustness property. We further establish conditions under which DoubleGen achieves oracle optimality -- matching the convergence rates standard approaches would enjoy if interventional data were available -- and minimax rate optimality. We illustrate DoubleGen with three examples: diffusion models, flow matching, and autoregressive language models.