Matching is a popular approach in causal inference to estimate treatment effects by pairing treated and control units that are most similar in terms of their covariate information. However, classic matching methods completely ignore the geometry of the data manifold, which is crucial to define a meaningful distance for matching, and struggle when covariates are noisy and high-dimensional. In this work, we propose GeoMatching, a matching method to estimate treatment effects that takes into account the intrinsic data geometry induced by existing causal mechanisms among the confounding variables. First, we learn a low-dimensional, latent Riemannian manifold that accounts for uncertainty and geometry of the original input data. Second, we estimate treatment effects via matching in the latent space based on the learned latent Riemannian metric. We provide theoretical insights and empirical results in synthetic and real-world scenarios, demonstrating that GeoMatching yields more effective treatment effect estimators, even as we increase input dimensionality, in the presence of outliers, or in semi-supervised scenarios.
Representation Learning Preserving Ignorability and Covariate Matching for Treatment Effects
Indian Institute of Science Education and Research, Bhopal(印度科学教育与研究学院,布巴兰普尔);Indian Institute of Science, Bangalore(印度科学研究院,班加罗尔);Indraprastha Institute of Information Technology, Delhi(印度理工信息学院,德里);Google Deepmind, Bangalore(谷歌DeepMind,班加罗尔)
Preference-based Conditional Treatment Effects and Policy Learning
Technion – Israel Institute of Technology(技术学院——以色列理工学院);Inria(法国国家信息与自动化技术研究所);Inserm(法国国家医学研究院);Université de Montpellier(蒙彼利埃大学);Department of Statistics and Operations Research, Tel Aviv University(特拉维夫大学统计与运筹学系)
Safe and Interpretable Estimation of Optimal Treatment Regimes
Johns Hopkins University(约翰斯·霍普金斯大学);Duke University(杜克大学);Harvard Medical School(哈佛医学院);Massachusetts General Hospital(麻省总医院);Beth Israel Deaconess Medical Center(贝斯以色列女执事医疗中心)