To produce the experiments in the main paper, run "Private_Fast_Mixing_OLS.py", and pick the dataset in Line 496.

For simulating the YearsMSD dataset, first download the dataset from "https://archive.ics.uci.edu/dataset/203/yearpredictionmsd" and extract the .txt file to the "datasets" folder. For simulating the Beijing and Rossman datasets, first unzip the .csv files from the corresponding zipped versions inside the "datasets" folder.

To produce the airline experiments from Appendix. J, run "Private_Fast_Mixing_OLS_Time_Accuracy.py", and pick the dataset in Line 655.

The conda environment used for running the experiments is inside environment.yml