On the Theoretical Properties of the Network Jackknife

Authors: Qiaohui Lin, Robert Lunde, Purnamrita Sarkar

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

Reproducibility Variable Result LLM Response
Research Type Experimental We complement our theoretical analysis with a range of simulated and real-data examples and show that the network jackknife offers competitive performance in cases where other resampling methods are known to be valid.
Researcher Affiliation Academia 1Department of Statistics and Data Sciences, University of Texas at Austin, TX, USA.
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide concrete access to source code for the methodology described.
Open Datasets Yes In the second experiment, we look at three college pairs: Berkeley and Stanford, Yale and Princeton, Harvard and MIT. First we decide which statistic differentiates between a given pair. For this, we split each college data set in half, into a training set and test set... We use Facebook network data (Rossi & Ahmed, 2015).
Dataset Splits No The paper mentions splitting data into "training set" and "test set" but does not explicitly mention a "validation" split.
Hardware Specification No The paper does not explicitly describe the hardware used to run its experiments.
Software Dependencies No The paper does not provide specific software dependencies with version numbers.
Experiment Setup Yes From these two graphons, we consider graph size n of n = 100, 500, 1000, 2000, 3000. For each n, we simulated 100 graphs to calculate the approximate true variance of edge density, triangle density, two-star density and normalized transitivity among these graphs. ... For this, we split each college data set in half, into a training set and test set.