Code for replication of "Regularizing Towards Causal Invariance: Linear Models with Proxies"

Section 5 (Synthetic Experiments): synthetic-experiments, depends on
- Computation: numpy, pandas, tqdm
- Plotting: R, with tidyverse, dplyr, readr, ggplot2, tikzDevice
Section 6 (Pollution): real-data-experiment, depends on
- Computation: Pandas, numpy, scipy, scikit-learn
- Notebooks: jupyter
- Plotting: seaborn, matplotlib