Nonlinear Sufficient Dimension Reduction for Causal Inference with Continuous Treatments
Abstract
Causal inference with continuous treatments requires estimating nuisance functions to adjust for the potentially high-dimensional confounder, but nonparametric estimation of these functions is severely hampered by the curse of dimensionality. To address this challenge, we propose a nonlinear sufficient dimension reduction framework to construct low-dimensional sufficient confounders to preserve the unbiasedness of the treatment effect. We estimate the causal effect by combining the generalized Sliced Inverse Regression with the inverse probability weighting, outcome regression, and augmented inverse probability weighting, respectively. We further establish the convergence rates of the first two estimators and derive the asymptotic distributions of the third. Our theoretical results show that, compared to estimators based on the full covariates, dimension reduction yields faster convergence rates and weaker rate conditions without inflating the asymptotic variance. Simulation studies demonstrate that the proposed estimators improve finite-sample performance over their counterparts without dimension reduction, particularly when the original covariate dimension is high. These results demonstrate that sufficient dimension reduction provides a flexible approach to mitigating the curse of dimensionality in causal inference with continuous treatments.
Related
- Belted Engression: Sufficient Dimension Reduction for Generative Distributional Regression
- Nondegenerate gradient Young measures and dimension reduction for nonlinear membranes
- Necessary and Sufficient Conditions for Adaptive Stabilizability of Continuous-Time Markov Jump Linear Stochastic Systems
- Necessary and Sufficient Criteria for Global PID Regulation of Nonlinear Uncertain System
- Balancing Covariates for Continuous Treatments by Exploiting Continuity
BibTeX
@misc{choi2026nonlinear,
title = {{Nonlinear Sufficient Dimension Reduction for Causal Inference with Continuous Treatments}},
author = {Chak Fung Choi and Yin Tang and Bing Li},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.39422},
eprint = {2610.39422},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.39422},
}
RIS
TY - UNPB
TI - Nonlinear Sufficient Dimension Reduction for Causal Inference with Continuous Treatments
AU - Chak Fung Choi
AU - Yin Tang
AU - Bing Li
PY - 2026
DA - 2026/10/29
PB - arXiv
DO - 10.48550/arxiv.2610.39422
UR - https://arxiv.org/abs/2610.39422
AB - Causal inference with continuous treatments requires estimating nuisance functions to adjust for the potentially high-dimensional confounder, but nonparametric estimation of these functions is severely hampered by the curse of dimensionality. To address this challenge, we propose a nonlinear sufficient dimension reduction framework to construct low-dimensional sufficient confounders to preserve the unbiasedness of the treatment effect. We estimate the causal effect by combining the generalized Sliced Inverse Regression with the inverse probability weighting, outcome regression, and augmented inverse probability weighting, respectively. We further establish the convergence rates of the first two estimators and derive the asymptotic distributions of the third. Our theoretical results show that, compared to estimators based on the full covariates, dimension reduction yields faster convergence rates and weaker rate conditions without inflating the asymptotic variance. Simulation studies demonstrate that the proposed estimators improve finite-sample performance over their counterparts without dimension reduction, particularly when the original covariate dimension is high. These results demonstrate that sufficient dimension reduction provides a flexible approach to mitigating the curse of dimensionality in causal inference with continuous treatments.
ER -