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-corrected stochastic sampler based on a Gaussian-smoothed interpolation. Our main theoretical contribution is a coupling-sensitive KL bound for constant-step Euler discretization: the error is controlled by moments of the source--target displacement under the chosen coupling, rather than by global uniform regularity of the velocity field, and has near-linear dependence on the ambient dimension. We also establish finite-sample non-parametric guarantees for the learned velocity and score fields when both the conditional outcome model and the source-target coupling are estimated from data. These bounds separate approximation, coupling-replacement, nuisance-estimation, generalization, and Monte Carlo errors and, combined with the sampler analysis, yield an end-to-end guarantee for counterfactual generation. Experiments on synthetic and semi-synthetic image benchmarks support the coupling-dependent theory and show that, at finite discretization budgets, the stochastic sampler can outperform the corresponding deterministic ODE sampler.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Guan, Y., Balasubramanian, K., & Kasiviswanathan, S. P. (2026). Counterfactual Generation via Flow Matching: Coupling-Sensitive End-to-End Rates. https://omanscience.com/en/articles/counterfactual-generation-via-flow-matching-coupling-sensitive-end-to-end-rates
MLA 9
Guan, Yunrui, et al. "Counterfactual Generation via Flow Matching: Coupling-Sensitive End-to-End Rates." https://omanscience.com/en/articles/counterfactual-generation-via-flow-matching-coupling-sensitive-end-to-end-rates.
Chicago (author–date)
Guan, Yunrui, Krishnakumar Balasubramanian, and Shiva Prasad Kasiviswanathan. 2026. "Counterfactual Generation via Flow Matching: Coupling-Sensitive End-to-End Rates." https://omanscience.com/en/articles/counterfactual-generation-via-flow-matching-coupling-sensitive-end-to-end-rates.
Harvard
Guan, Y., Balasubramanian, K. and Kasiviswanathan, S. P. (2026) 'Counterfactual Generation via Flow Matching: Coupling-Sensitive End-to-End Rates', Available at: https://omanscience.com/en/articles/counterfactual-generation-via-flow-matching-coupling-sensitive-end-to-end-rates.
Vancouver
Guan Y, Balasubramanian K, Kasiviswanathan SP. Counterfactual Generation via Flow Matching: Coupling-Sensitive End-to-End Rates. https://omanscience.com/en/articles/counterfactual-generation-via-flow-matching-coupling-sensitive-end-to-end-rates
IEEE
Y. Guan, K. Balasubramanian, and S. P. Kasiviswanathan, "Counterfactual Generation via Flow Matching: Coupling-Sensitive End-to-End Rates," https://omanscience.com/en/articles/counterfactual-generation-via-flow-matching-coupling-sensitive-end-to-end-rates.