Efficient Causal Inference from Combined Observational and Interventional Data through Causal Reductions
Maximilian Ilse ([email protected]), Patrick Forré, Max Welling, and Joris M. Mooij
PyTorch implementation of our paper "Efficient Causal Inference from Combined Observational and Interventional Data through Causal Reductions". https://arxiv.org/abs/2103.04786
Besides the original code this repository contains a notebook for people that are new to Pytorch and normalizing flows. We recommend to open the notebook directly in Google Colab: https://colab.research.google.com/github/max-ilse/CausalReduction/blob/main/spline_flow_joint.ipynb, Google Colab allows you to run the code in your browser without configuring Python or Pytorch.