Network reconstruction via the minimum description length principle

arXiv:2405.01015v1 Announce Type: cross
Abstract: A fundamental problem associated with the task of network reconstruction from dynamical or behavioral data consists in determining the most appropriate model complexity in a manner that prevents overfitting, and produces an inferred network with a statistically justifiable number of edges. The status quo in this context is based on $L_{1}$ regularization combined with cross-validation. As we demonstrate, besides its high computational cost, this commonplace approach unnecessarily ties the promotion of sparsity with weight "shrinkage". …

abstract arxiv behavioral data complexity context cs.lg cs.si data fundamental minimum network overfitting physics.data-an q-bio.pe stat.ml type via