Revealing Common Statistical Behaviors in Heterogeneous Populations

Authors: Andrey Zhitnikov, Rotem Mulayoff, Tomer Michaeli

ICML 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We illustrate the effectiveness of our methods through extensive simulations as well as on real-data from f MRI scans and from arterial blood pressure and photoplethysmogram measurements.
Researcher Affiliation Academia Electrical Engineering Dept., Technion, Israel.
Pseudocode Yes Algorithm 1 Common covariance estimation. ... Algorithm 2 Common density estimation.
Open Source Code No The paper does not provide any explicit statements or links indicating that the source code for the methodology is open-sourced or publicly available.
Open Datasets Yes ADHD200-preprocessed dataset (Bellec et al., 2017). ... MIMIC 2 dataset (Kachuee et al., 2015).
Dataset Splits No The paper uses datasets but does not explicitly provide details on train/validation/test splits, specific percentages, or sample counts for reproducing data partitioning.
Hardware Specification Yes The running time of Alg. 1 was about 10s on an 8 core Intel i7-6700 with 16GB of RAM working at 3.40GHz.
Software Dependencies No We used the nilearn and scikit-learn python packages (Abraham et al., 2014; Pedregosa et al., 2011; Buitinck et al., 2013).
Experiment Setup Yes In particular, we used preprocessed resting state f MRI data... We removed nuisance variance... applied a temporal bandpass filter (0.009 Hz < f < 0.08 Hz) ... and a spatial Gaussian filter (6mm FWHM). ... For each subject, we then estimated the 2D pdf of ABP and PPG using Gaussian KDE with bandwidth 0.08.