A novel problem of improving causal effect estimation accuracy with the help of knowledge transfer under the same covariate (or feature) space setting, i.e., homogeneous transfer learning (TL), is studied, referred to as the Transfer Causal Learning (TCL) problem. While most recent efforts in adapting TL techniques to estimate average causal effect (ACE) have been focused on the heterogeneous covariate space setting, those methods are inadequate for tackling the TCL problem since their algorithm designs are based on the decomposition into shared and domain-specific covariate spaces. To address this issue, we propose a generic framework called $\ell_1$-TCL, which incorporates $\ell_1$ regularized TL for nuisance parameter estimation and downstream plug-in ACE estimators, including outcome regression, inverse probability weighted, and doubly robust estimators. Most importantly, with the help of Lasso for high-dimensional regression, we establish non-asymptotic recovery guarantees for the generalized linear model (GLM) under the sparsity assumption for the proposed $\ell_1$-TCL. From an empirical perspective, $\ell_1$-TCL is a generic learning framework that can incorporate not only GLM but also many recently developed non-parametric methods, which can enhance robustness to model mis-specification. We demonstrate this empirical benefit through extensive numerical simulation by incorporating both GLM and recent neural network-based approaches in $\ell_1$-TCL, which shows improved performance compared with existing TL approaches for ACE estimation. Furthermore, our $\ell_1$-TCL framework is subsequently applied to a real study, revealing that vasopressor therapy could prevent 28-day mortality within septic patients, which all baseline approaches fail to show.

翻译：本文研究了一个新问题——在同协变量（或特征）空间设置下，通过知识迁移提升因果效应估计精度，即同质迁移学习，称之为迁移因果学习（TCL）问题。尽管近期将迁移学习技术用于估计平均因果效应（ACE）的研究大多聚焦于异质协变量空间设置，但这些方法因算法设计依赖于共享与领域特定协变量空间的分解，难以有效解决TCL问题。为此，我们提出一个通用框架——ℓ₁-TCL，该框架融入ℓ₁正则化迁移学习以估计 nuisance 参数，并结合下游的即插即用型ACE估计器，包括结果回归、逆概率加权和双重稳健估计器。最重要的是，借助Lasso在高维回归中的优势，我们在稀疏性假设下为广义线性模型（GLM）建立了所提ℓ₁-TCL框架的非渐近恢复保证。从实证角度看，ℓ₁-TCL是一个通用学习框架，不仅可整合GLM，还能融入近年来发展的多种非参数方法，从而增强对模型误设的鲁棒性。通过在ℓ₁-TCL中整合GLM及基于神经网络的最新方法，我们通过大量数值模拟验证了其实证优势，结果显示其相比现有ACE估计的迁移学习方法性能更优。此外，我们将ℓ₁-TCL框架应用于一项真实研究，发现血管升压药治疗可降低脓毒症患者28天死亡率，而所有基线方法均未能揭示该结论。