Towards Clarifying the Theory of the Deconfounder

by Yixin Wang & David M. Blei

Keywords: Causal inference, Machine learning, Probabilistic models, Unconfoundedness, Unobserved confounding

Abstract

Wang and Blei (2019) studies multiple causal inference and proposes the deconfounder algorithm. The paper discusses theoretical requirements and presents empirical studies. Several refinements have been suggested around the theory of the deconfounder. Among these, Imai and Jiang clarified the assumption of “no unobserved single-cause confounders.” Using their assumption, this paper clarifies the theory. Furthermore, Ogburn et al. (2020) proposes counterexamples to the theory. But the proposed counterexamples do not satisfy the required assumptions.