Equivalence of Graphical Lasso and Thresholding for Sparse Graphs

Authors: Somayeh Sojoudi

JMLR 2016 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Simulations on random systems are provided in Section 3. Two case studies on fMRI data and electrical circuits are conducted in Sections 4 and 5, respectively.
Researcher Affiliation Academia Somayeh Sojoudi, EMAIL Department of Electrical Engineering and Computer Sciences University of California, Berkeley
Pseudocode No The paper describes mathematical derivations and conditions for equivalence. It does not contain structured pseudocode or algorithm blocks.
Open Source Code No The paper does not explicitly provide concrete access to source code for the methodology described in this paper.
Open Datasets Yes These fMRI data sets are borrowed form Vertes et al. (2012).
Dataset Splits No The paper mentions data properties like 'Each data set includes 134 samples of the low frequency oscillations, taken at 140 cortical brain regions' and 'For r = 99 and 10 different trials, we have calculated the sample covariance matrices', but does not provide specific train/test/validation dataset splits.
Hardware Specification No The paper does not provide specific hardware details used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details with version numbers needed to replicate the experiment.
Experiment Setup Yes We choose the regularization parameter λ in the graphical lasso algorithm and the level of thresholding in such a way that they both lead to graphs with n - 1 = 139 edges.