arXiv：cs.LG· Christophe Muller, Ayub Kharel, Alex Luedtke, Chan Park, Eric Tchetgen Tchetgen, Juan L. Gamella, Rahul Krishnan, Ricardo Silva, Jakob Zeitler·· 6 小时前AI 评分34
ProximalFM：隐藏混杂下的摊销近端因果推断
ProximalFM: Amortized Proximal Causal Inference under Hidden Confounding
AI 导读
针对隐藏混杂下近端因果推断中非参数估计需求解病态积分方程、数据需求大且优化不稳定的问题，研究者提出 ProximalFM，用先验数据拟合网络（PFN）将贝叶斯算子反演摊销为单次 Transformer 前向传播。
正文
Abstract:Standard causal identification methods often assume no unmeasured confounding and can fail when relevant confounders are unobserved. Proximal causal inference instead uses proxy variables to identify effects under hidden confounding. However, nonparametric proximal estimation can be challenging in practice: recovering causal estimands such as the conditional average treatment effect (CATE) requires solving an ill-posed integral equation that is data-hungry, hyperparameter-sensitive, and optimization-unstable. Bayesian inference for such models provides a desirable alternative, mitigating these difficulties by regularizing through the prior. However, computing a posterior is itself challenging, as a typical likelihood function will include latent variables. Following the recent success of tabular foundation models in backdoor, instrumental variable, and frontdoor settings, we propose that prior-data fitted networks (PFNs) are uniquely suited to resolve this bottleneck. Indeed, by training on synthetic data sampled from compliant structural causal models with access to oracle counterfactuals, we simplify the task substantially, amortizing the implied Bayesian operator inversion into a single transformer forward pass. Compared to prior literature that focuses primarily on point estimation, our model, ProximalFM, explicitly targets the Bayesian posterior distribution of the CATE. One unique aspect of this problem is that we need to provide Monte Carlo estimates of the oracle CATEs, leading to a novel variation of PFNs that accounts for the added stochastic error. Across a diverse suite of proximal regimes, ProximalFM achieves consistently strong CATE-estimation performance without dataset-specific tuning, with its largest advantage when latent confounding is substantial and the proxies are weakly informative; it also provides fast inference through a single amortized forward pass.
| Subjects: | Machine Learning (stat.ML); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.08078 [stat.ML] |
| (or arXiv:2610.08078v1 [stat.ML] for this version) | |
| https://doi.org/10.48550/arXiv.2610.08078 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Christophe Muller [view email]
[v1]
Tue, 6 Oct 2026 10:07:19 UTC (8,424 KB)
来源：arXiv：cs.LG · arxiv.org