Deep Learning of Potential Outcomes

Authors:
  • BKBernard Koch
    Bernard Koch
  • TSTim Sainburg
    Tim Sainburg
  • PGPablo Geraldo
    Pablo Geraldo
  • SJSong Jiang
    Song Jiang
  • YSYizhou Sun
    Yizhou Sun
  • JFJacob Gates Foster
    Jacob Gates Foster

Abstract
This review systematizes the emerging literature for causal inference using deep neural networks under the potential outcomes framework. It provides an intuitive introduction on how deep learning can be used to estimate/predict heterogeneous treatment effects and extend causal inference to settings where confounding is non-linear, time varying, or encoded in text, networks, and images. To maximize accessibility, we also introduce prerequisite concepts from causal inference and deep learning. The survey differs from other treatments of deep learning and causal inference in its sharp focus on observational causal estimation, its extended exposition of key algorithms, and its detailed tutorials for implementing, training, and selecting among deep estimators in Tensorflow 2 available at github.com/kochbj/Deep-Learning-for-Causal-Inference.