aiqbench analysis
This research introduces PCL-U, a novel framework that automatically learns proxy variables to address unmeasured confounding in causal inference from observational data. By utilizing neural encoders and minimax mutual information objectives, the method decomposes covariates into specific treatment- and outcome-inducing components without requiring pre-specified proxies. Experimental results on benchmarks and synthetic datasets demonstrate that this approach maintains stable estimation accuracy while matching or exceeding existing baselines.
Proximal Causal Learning under Unmeasured Confounding
arXiv:2610.04519v1 Announce Type: new Abstract: Estimating treatment effects from observational data typically relies on the No Unmeasured Confounding Assumption (NUCA), which rarely holds in practice. Proximal causal learning (PCL) addresses unmeasured confounding via proxy variables, yet existing methods require the proxy variables to be pre-specified. Thus, we propose PCL-U, a framework that learns proxy variables directly from observed covariates. PCL-U uses neural encoders to decompose covariates into treatment-inducing, outcome-inducing, and shared proxies, guided by minimax mutual information objectives, and obtains causal estimates through a practical moment-based risk function. Experiments on benchmarks show that PCL-U matches or outperforms existing baselines. Besides, there are two types of synthetic datasets with varying dimensions and confounding strengths that illustrate that our method maintains stable estimation accuracy.
Abstract:Estimating treatment effects from observational data typically relies on the No Unmeasured Confounding Assumption (NUCA), which rarely holds in practice. Proximal causal learning (PCL) addresses unmeasured confounding via proxy variables, yet existing methods require the proxy variables to be pre-specified. Thus, we propose PCL-U, a framework that learns proxy variables directly from observed covariates. PCL-U uses neural encoders to decompose covariates into treatment-inducing, outcome-inducing, and shared proxies, guided by minimax mutual information objectives, and obtains causal estimates through a practical moment-based risk function. Experiments on benchmarks show that PCL-U matches or outperforms existing baselines. Besides, there are two types of synthetic datasets with varying dimensions and confounding strengths that illustrate that our method maintains stable estimation accuracy.
Machine Learning (cs.LG)
arXiv:2610.04519 [cs.LG]
(or arXiv:2610.04519v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2610.04519 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 211 words
Related coverage
Proximal Balancing for Causal Effect Estimation under Unmeasured Confounding
arXiv · Oct 1, 2026
Flexible Doubly Robust Proximal Causal Inference for Censored Outcomes
arXiv · Oct 16, 2026
ProximalFM: Amortized Proximal Causal Inference under Hidden Confounding
arXiv · Oct 7, 2026
Blessing from Human-AI Interaction: Super Reinforcement Learning in Confounded Environments
arXiv · Jun 5, 2026