NeurIPS 2020

Estimating the Effects of Continuous-valued Interventions using Generative Adversarial Networks

Meta Review

The paper studies the problem of estimating the effect of continuous treatment variables. The authors propose a GAN-based framework to learns the distribution of the unobserved counterfactuals. The reviewers found the theoretical contribution as well as the simulation showing improvement over the pre-existing benchmarks satisfying. Estimating the effect of a treatment is a central problem to causal inference and as such this paper could be of interest to the broader NeurIPS audience.