Model-Powered Conditional Independence Test

Authors: Rajat Sen, Ananda Theertha Suresh, Karthikeyan Shanmugam, Alexandros G. Dimakis, Sanjay Shakkottai

NeurIPS 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We empirically validate the performance of our algorithm on simulated and real datasets and show performance gains over previous methods.
Researcher Affiliation Collaboration Rajat Sen1,*, Ananda Theertha Suresh2,*, Karthikeyan Shanmugam3,*, Alexandros G. Dimakis1, and Sanjay Shakkottai1 1The University of Texas at Austin 2Google, New York 3IBM Research, Thomas J. Watson Center
Pseudocode Yes Algorithm 1 Data Gen ... Algorithm 2 CCITv1 ... Algorithm 3 CCITv2
Open Source Code Yes The python package for our implementation can be found here (https://github.com/rajatsen91/CCIT).
Open Datasets Yes We also apply our algorithm for analyzing CI relations in the protein signaling network data from the flow cytometry data-set [26]. ... Karen Sachs, Omar Perez, Dana Pe er, Douglas A Lauffenburger, and Garry P Nolan. Causal protein-signaling networks derived from multiparameter single-cell data. Science, 308(5721):523 529, 2005.
Dataset Splits Yes Divide data-set D into train and test set Dr and De respectively. Note that |Dr| = |De| = n.
Hardware Specification No The paper does not specify any hardware components such as CPU, GPU, or memory used for running the experiments.
Software Dependencies No The paper mentions using 'XGBoost [6]' and a 'python package for our implementation' but does not provide specific version numbers for these software dependencies.
Experiment Setup Yes In these experiments the number of bootstraps per data-set for CCIT was set to B = 50. We set the threshold in Algorithm 3 to = 1/pn, which is an upper-bound on the expected variance of the test-statistic when H0 holds.