Goodness-of-Fit Tests for Inhomogeneous Random Graphs

Authors: Soham Dan, Bhaswar B. Bhattacharya

ICML 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We compare the performances of the different tests in simulations, and show that the proposed tests outperform the baseline tests across various natural random graphs models.
Researcher Affiliation Academia 1Department of Computer and Information Science, University of Pennsylvania, Philadelphia, USA, 2Department of Statistics, University of Pennsylvania, Philadelphia, USA.
Pseudocode Yes Algorithm 1 Bootstrapping a Test Statistic
Open Source Code No The paper does not provide an explicit statement or link for the open-source code of the described methodology.
Open Datasets No The paper describes generating data from models like Erd os-R enyi and Planted Bisection for simulations, but does not refer to external publicly available datasets for training.
Dataset Splits No The paper uses the term 'validate' in the context of validating asymptotic results through simulation, not referring to a validation dataset split.
Hardware Specification No The paper does not provide any specific details about the hardware used for running experiments or simulations.
Software Dependencies No The paper does not provide specific software dependencies with version numbers.
Experiment Setup Yes For our simulations, we fix the size of the graph n = 100, the sample size m = 4, and a reference edge-probability matrix Q(n) (which corresponds to the null), and consider samples G1, G2, G3, G4 i.i.d from IER(P (n)), where P (n) is a certain perturbation of the Q(n). The figures below show the empirical power of the tests over 1000 iterations (calibrated either using the asymptotic distribution or the parametric bootstrap at level α = 0.05) as the perturbation parameter increases.