Counterfactual Generation via Flow Matching: Coupling-Sensitive End-to-End Rates

Excerpt

arXiv:2610.01193v1 Announce Type: new Abstract: Counterfactual generation seeks to sample outcomes under a hypothetical intervention or decision using observational data collected under the factual assignment mechanism. We develop a flow-matching approach that combines a sample-split, doubly robust training objective with a learned coupling between observed source outcomes and target outcomes drawn from a fitted conditional outcome model. To enable finite-step generation, we leverage a score-cor