Kernel Conditional Independence Permutation Test
Matlab Shell
Switch branches/tags
Nothing to show
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Failed to load latest commit information.
data
experiments
kcipt
results
.gitignore
LICENSE
README.md
run_chsic_chaotic.m
run_chsic_postnonlinear.m
run_digoxin_pc.m
run_kcipt_bootstrap.m
run_kcipt_chaotic.m
run_kcipt_postnonlinear.m
run_kcit_chaotic.m
run_kcit_postnonlinear.m
run_permutation_comparison.m
setup.sh

README.md

KCIPT: Kernel Conditional Independence Permutation Test

Gary Doran (gary.doran@case.edu)

Overview

This repository includes MATLAB code for the Kernel Conditional Independence Permutation Test (KCIPT) as introduced in:

Doran, Gary, Krikamol Muandet, Kun Zhang, and Bernhard Schölkopf. A Permutation-Based Kernel Conditional Independence Test. To appear in the 30th Conference on Uncertainty in Artificial Intelligence. 2014.

Setup

The code in this repository depends on the implementations of prior approaches, found here, and an implementation of the PC algorithm, found here. A BASH script has been included that automatically fetches these dependencies:

$ ./setup.sh

Running the Experiments

The MATLAB scripts in the root of this repository can be used to run all experiments found in the paper. By default, results are stored in the results directory. In practice, the individual experiments were run on a computing cluster, and a copy of the results can be found here.