Learning the Structure of Large Networked Systems Obeying Conservation Laws

Authors: Anirudh Rayas, Rajasekhar Anguluri, Gautam Dasarathy

NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Finally, we complement our theoretical results with experimental validation of the performance of the proposed estimator on synthetic and real-world data.
Researcher Affiliation Academia Anirudh Rayas Arizona State University ahrayas@asu.edu Rajasekhar Anguluri Arizona State University rangulur@asu.edu Gautam Dasarathy Arizona State University gautamd@asu.edu
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code No The code and it s related details will be made available in the appendix.
Open Datasets Yes We validate the support recovery performance of our 1-regularized MLE on synthetic and a benchmark power distribution network (see Fig. 2). ... (ii) Power network: We set B to be the Laplacian of the IEEE 33 bus power distribution network [69].
Dataset Splits No The paper mentions using samples of Y and averaging results over 100 trials but does not specify a train/validation/test split or cross-validation setup for specific datasets.
Hardware Specification No The paper states 'These [total amount of compute and type of resources] will be mentioned in the appendix', indicating that specific hardware details are not present in the current document.
Software Dependencies No The paper does not provide specific software dependencies with version numbers.
Experiment Setup Yes We choose λn proportional to log p/n. Our results are averaged over 100 trials of n independent samples of Y. We compare 1-regularized MLE performance with (i) the square-root estimator (hereafter, GLASSO+SR) that identifies the support of B by determining (i, j) for which b 1 2 i,j 6= 0; and (ii) the GLASSO+2HR (Hop Refinement) estimator [20] that identifies the support of B by determining (i, j) for which b i,j for = 1e 02.