Deep Proxy Causal Learning and its Application to Confounded Bandit Policy Evaluation

arXiv:2106.03907v4 Announce Type: replace
Abstract: Proxy causal learning (PCL) is a method for estimating the causal effect of treatments on outcomes in the presence of unobserved confounding, using proxies (structured side information) for the confounder. This is achieved via two-stage regression: in the first stage, we model relations among the treatment and proxies; in the second stage, we use this model to learn the effect of treatment on the outcome, given the context provided by the proxies. PCL guarantees recovery …

abstract application arxiv confounding cs.lg evaluation information policy proxies regression relations stage stat.ml type via