Keywords: VAE, variational autoencoder, balanced representation Learning, treatment effects, causal inference, identifiability, identification, CATE, ATE, weak overlap, limited overlap, Prognostic Model, Prognostic score
TL;DR: Weak overlap, prognostic score, identifiable VAE, balanced representation Learning, counterfactual generalization bounds, all in one paper.
Abstract: As an important problem of causal inference, we discuss the identification and estimation of treatment effects (TEs) under weak overlap, i.e., subjects with certain features all belong to a single treatment group. We use a latent variable to model a prognostic score (PGS), which is widely used in biostatistics and sufficient for TEs, i.e., we build a generative prognostic model. We prove that the latent variable recovers a PGS, and the model identifies individualized treatment effects. The model is then learned as the Intact-VAE, a new type of variational autoencoder (VAE). We derive counterfactual generalization bounds which motivate representation balanced for treatment groups conditioned on individualized features. The proposed method is compared with recent methods using (semi-)synthetic datasets.
Supplementary Material: zip
Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.