Skip to content

Pytorch implementation of the multitasking RieszNet architecture for Auto-DML doubly-robust estimation of causal effects

License

Notifications You must be signed in to change notification settings

doctor-phil/PyRiesz

Repository files navigation

PyRiesz

Flexible PyTorch implementations of Auto-DML estimators of the Riesz Representer for causal effects estimation with machine learning.

Implements the multitask learning RieszNet architecture from Chernozhukov, Newey, Quintas-Martı́nez, and Syrgkanis (2022, PMLR), as well as the LASSO estimator of the Riesz representation described in Chernozhukov, Newey, and Singh (2022, Econometrica)

Installation

Install using pip install pyriesz

Documentation

Documentation for the key methods is available here

About

Pytorch implementation of the multitasking RieszNet architecture for Auto-DML doubly-robust estimation of causal effects

Resources

License

Stars

Watchers

Forks

Packages

No packages published