Skip to content
/ abpnl Public

A multivariate causal discovery based on post-nonlinear model

License

Notifications You must be signed in to change notification settings

rafcc/abpnl

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Autoencoder-based causal discovery based on multivariate post-nonlinear model

This is an official implementation of the multivariate nonlinear causal discovery method using post-nonlinear causal model in the following papers.

Requirements

  • python 3.10 (may work on >=3.8 but tested only on 3.10)
    • numpy
    • scipy
    • torch

Example

./sample.sh

See example.py for more details.

Note: If you use parallelization with max_workers parameter, it is recommended to disable Numpy's multithreading by, for example, export OMP_NUM_THREADS=1.

About

A multivariate causal discovery based on post-nonlinear model

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published