PO-Flow uses continuous normalizing flows trained via flow matching to jointly model potential outcome distributions and enable factual-conditioned counterfactual prediction for causal inference tasks including CATE estimation.
Normalizing flow neural networks by jko scheme,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Flow-based Generative Modeling of Potential Outcomes and Counterfactuals
PO-Flow uses continuous normalizing flows trained via flow matching to jointly model potential outcome distributions and enable factual-conditioned counterfactual prediction for causal inference tasks including CATE estimation.